fix(proxy): ensure OpenAI tool call streaming emits proper delta chunks and increase body limit

- Emit tool call id+name in first SSE delta and arguments in subsequent deltas
- Split large tool arguments into 1000-char chunks to prevent framing issues
- Set FastifyAdapter bodyLimit to 10MB to handle large payloads
- Add TDD tests for tool call streaming verification

.agent/skills/openspec-apply-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Implement tasks from an OpenSpec change.
@@ -25,9 +25,11 @@ Implement tasks from an OpenSpec change.
    Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
 
 2. **Check status to understand the schema**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand:
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
@@ -139,6 +141,7 @@ What would you like to do?
 ```
 
 **Guardrails**
+
 - Keep going through tasks until done or blocked
 - Always read context files before starting (from the apply instructions output)
 - If task is ambiguous, pause and ask before implementing

.agent/skills/openspec-archive-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Archive a completed change in the experimental workflow.
@@ -68,6 +68,7 @@ Archive a completed change in the experimental workflow.
 5. **Perform the archive**
 
    Create the archive directory if it doesn't exist:
+
    ```bash
    mkdir -p openspec/changes/archive
    ```
@@ -105,6 +106,7 @@ All artifacts complete. All tasks complete.
 ```
 
 **Guardrails**
+
 - Always prompt for change selection if not provided
 - Use artifact graph (openspec status --json) for completion checking
 - Don't block archive on warnings - just inform and confirm

.agent/skills/openspec-bulk-archive-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Archive multiple completed changes in a single operation.
@@ -37,16 +37,16 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    For each selected change, collect:
 
    a. **Artifact status** - Run `openspec status --change "<name>" --json`
-      - Parse `schemaName` and `artifacts` list
-      - Note which artifacts are `done` vs other states
+   - Parse `schemaName` and `artifacts` list
+   - Note which artifacts are `done` vs other states
 
    b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
-      - Count `- [ ]` (incomplete) vs `- [x]` (complete)
-      - If no tasks file exists, note as "No tasks"
+   - Count `- [ ]` (incomplete) vs `- [x]` (complete)
+   - If no tasks file exists, note as "No tasks"
 
    c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
-      - List which capability specs exist
-      - For each, extract requirement names (lines matching `### Requirement: <name>`)
+   - List which capability specs exist
+   - For each, extract requirement names (lines matching `### Requirement: <name>`)
 
 4. **Detect spec conflicts**
 
@@ -66,18 +66,18 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
 
    b. **Search the codebase** for implementation evidence:
-      - Look for code implementing requirements from each delta spec
-      - Check for related files, functions, or tests
+   - Look for code implementing requirements from each delta spec
+   - Check for related files, functions, or tests
 
    c. **Determine resolution**:
-      - If only one change is actually implemented -> sync that one's specs
-      - If both implemented -> apply in chronological order (older first, newer overwrites)
-      - If neither implemented -> skip spec sync, warn user
+   - If only one change is actually implemented -> sync that one's specs
+   - If both implemented -> apply in chronological order (older first, newer overwrites)
+   - If neither implemented -> skip spec sync, warn user
 
    d. **Record resolution** for each conflict:
-      - Which change's specs to apply
-      - In what order (if both)
-      - Rationale (what was found in codebase)
+   - Which change's specs to apply
+   - In what order (if both)
+   - Rationale (what was found in codebase)
 
 6. **Show consolidated status table**
 
@@ -93,12 +93,14 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    For conflicts, show the resolution:
+
    ```
    * Conflict resolution:
      - auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
    ```
 
    For incomplete changes, show warnings:
+
    ```
    Warnings:
    - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
@@ -107,7 +109,6 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 7. **Confirm batch operation**
 
    Use **AskUserQuestion tool** with a single confirmation:
-
    - "Archive N changes?" with options based on status
    - Options might include:
      - "Archive all N changes"
@@ -121,20 +122,21 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    Process changes in the determined order (respecting conflict resolution):
 
    a. **Sync specs** if delta specs exist:
-      - Use the openspec-sync-specs approach (agent-driven intelligent merge)
-      - For conflicts, apply in resolved order
-      - Track if sync was done
+   - Use the openspec-sync-specs approach (agent-driven intelligent merge)
+   - For conflicts, apply in resolved order
+   - Track if sync was done
 
    b. **Perform the archive**:
-      ```bash
-      mkdir -p openspec/changes/archive
-      mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
-      ```
+
+   ```bash
+   mkdir -p openspec/changes/archive
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
 
    c. **Track outcome** for each change:
-      - Success: archived successfully
-      - Failed: error during archive (record error)
-      - Skipped: user chose not to archive (if applicable)
+   - Success: archived successfully
+   - Failed: error during archive (record error)
+   - Skipped: user chose not to archive (if applicable)
 
 9. **Display summary**
 
@@ -157,6 +159,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    If any failures:
+
    ```
    Failed 1 change:
    - some-change: Archive directory already exists
@@ -165,6 +168,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 **Conflict Resolution Examples**
 
 Example 1: Only one implemented
+
 ```
 Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
 
@@ -180,6 +184,7 @@ Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
 ```
 
 Example 2: Both implemented
+
 ```
 Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
 
@@ -233,6 +238,7 @@ No active changes found. Use `/opsx:new` to create a new change.
 ```
 
 **Guardrails**
+
 - Allow any number of changes (1+ is fine, 2+ is the typical use case)
 - Always prompt for selection, never auto-select
 - Detect spec conflicts early and resolve by checking codebase

.agent/skills/openspec-continue-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Continue working on a change by creating the next artifact.
@@ -30,9 +30,11 @@ Continue working on a change by creating the next artifact.
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
 2. **Check current status**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand current state. The response includes:
    - `schemaName`: The workflow schema being used (e.g., "spec-driven")
    - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
@@ -40,7 +42,7 @@ Continue working on a change by creating the next artifact.
 
 3. **Act based on status**:
 
-   ---
+   ***
 
    **If all artifacts are complete (`isComplete: true`)**:
    - Congratulate the user
@@ -48,7 +50,7 @@ Continue working on a change by creating the next artifact.
    - Suggest: "All artifacts created! You can now implement this change or archive it."
    - STOP
 
-   ---
+   ***
 
    **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
    - Pick the FIRST artifact with `status: "ready"` from the status output
@@ -71,7 +73,7 @@ Continue working on a change by creating the next artifact.
    - Show what was created and what's now unlocked
    - STOP after creating ONE artifact
 
-   ---
+   ***
 
    **If no artifacts are ready (all blocked)**:
    - This shouldn't happen with a valid schema
@@ -85,6 +87,7 @@ Continue working on a change by creating the next artifact.
 **Output**
 
 After each invocation, show:
+
 - Which artifact was created
 - Schema workflow being used
 - Current progress (N/M complete)
@@ -98,6 +101,7 @@ The artifact types and their purpose depend on the schema. Use the `instruction`
 Common artifact patterns:
 
 **spec-driven schema** (proposal → specs → design → tasks):
+
 - **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
   - The Capabilities section is critical - each capability listed will need a spec file.
 - **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
@@ -107,6 +111,7 @@ Common artifact patterns:
 For other schemas, follow the `instruction` field from the CLI output.
 
 **Guardrails**
+
 - Create ONE artifact per invocation
 - Always read dependency artifacts before creating a new one
 - Never skip artifacts or create out of order

.agent/skills/openspec-explore/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
@@ -33,24 +33,28 @@ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wher
 Depending on what the user brings, you might:
 
 **Explore the problem space**
+
 - Ask clarifying questions that emerge from what they said
 - Challenge assumptions
 - Reframe the problem
 - Find analogies
 
 **Investigate the codebase**
+
 - Map existing architecture relevant to the discussion
 - Find integration points
 - Identify patterns already in use
 - Surface hidden complexity
 
 **Compare options**
+
 - Brainstorm multiple approaches
 - Build comparison tables
 - Sketch tradeoffs
 - Recommend a path (if asked)
 
 **Visualize**
+
 ```
 ┌─────────────────────────────────────────┐
 │     Use ASCII diagrams liberally        │
@@ -69,6 +73,7 @@ Depending on what the user brings, you might:
 ```
 
 **Surface risks and unknowns**
+
 - Identify what could go wrong
 - Find gaps in understanding
 - Suggest spikes or investigations
@@ -82,11 +87,13 @@ You have full context of the OpenSpec system. Use it naturally, don't force it.
 ### Check for context
 
 At the start, quickly check what exists:
+
 ```bash
 openspec list --json
 ```
 
 This tells you:
+
 - If there are active changes
 - Their names, schemas, and status
 - What the user might be working on
@@ -115,14 +122,14 @@ If the user mentions a change or you detect one is relevant:
 
 3. **Offer to capture when decisions are made**
 
-   | Insight Type | Where to Capture |
-   |--------------|------------------|
+   | Insight Type               | Where to Capture             |
+   | -------------------------- | ---------------------------- |
    | New requirement discovered | `specs/<capability>/spec.md` |
-   | Requirement changed | `specs/<capability>/spec.md` |
-   | Design decision made | `design.md` |
-   | Scope changed | `proposal.md` |
-   | New work identified | `tasks.md` |
-   | Assumption invalidated | Relevant artifact |
+   | Requirement changed        | `specs/<capability>/spec.md` |
+   | Design decision made       | `design.md`                  |
+   | Scope changed              | `proposal.md`                |
+   | New work identified        | `tasks.md`                   |
+   | Assumption invalidated     | Relevant artifact            |
 
    Example offers:
    - "That's a design decision. Capture it in design.md?"
@@ -147,6 +154,7 @@ If the user mentions a change or you detect one is relevant:
 ## Handling Different Entry Points
 
 **User brings a vague idea:**
+
 ```
 User: I'm thinking about adding real-time collaboration
 
@@ -170,6 +178,7 @@ You: Real-time collab is a big space. Let me think about this...
 ```
 
 **User brings a specific problem:**
+
 ```
 User: The auth system is a mess
 
@@ -201,6 +210,7 @@ You: [reads codebase]
 ```
 
 **User is stuck mid-implementation:**
+
 ```
 User: /opsx:explore add-auth-system
       The OAuth integration is more complex than expected
@@ -218,6 +228,7 @@ You: [reads change artifacts]
 ```
 
 **User wants to compare options:**
+
 ```
 User: Should we use Postgres or SQLite?
 

.agent/skills/openspec-ff-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Fast-forward through artifact creation - generate everything needed to start implementation in one go.
@@ -18,6 +18,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 1. **If no clear input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -25,15 +26,19 @@ Fast-forward through artifact creation - generate everything needed to start imp
    **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
 
 2. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    This creates a scaffolded change at `openspec/changes/<name>/`.
 
 3. **Get the artifact build order**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to get:
    - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
    - `artifacts`: list of all artifacts with their status and dependencies
@@ -45,30 +50,30 @@ Fast-forward through artifact creation - generate everything needed to start imp
    Loop through artifacts in dependency order (artifacts with no pending dependencies first):
 
    a. **For each artifact that is `ready` (dependencies satisfied)**:
-      - Get instructions:
-        ```bash
-        openspec instructions <artifact-id> --change "<name>" --json
-        ```
-      - The instructions JSON includes:
-        - `context`: Project background (constraints for you - do NOT include in output)
-        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
-        - `template`: The structure to use for your output file
-        - `instruction`: Schema-specific guidance for this artifact type
-        - `outputPath`: Where to write the artifact
-        - `dependencies`: Completed artifacts to read for context
-      - Read any completed dependency files for context
-      - Create the artifact file using `template` as the structure
-      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
-      - Show brief progress: "✓ Created <artifact-id>"
+   - Get instructions:
+     ```bash
+     openspec instructions <artifact-id> --change "<name>" --json
+     ```
+   - The instructions JSON includes:
+     - `context`: Project background (constraints for you - do NOT include in output)
+     - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+     - `template`: The structure to use for your output file
+     - `instruction`: Schema-specific guidance for this artifact type
+     - `outputPath`: Where to write the artifact
+     - `dependencies`: Completed artifacts to read for context
+   - Read any completed dependency files for context
+   - Create the artifact file using `template` as the structure
+   - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+   - Show brief progress: "✓ Created <artifact-id>"
 
    b. **Continue until all `applyRequires` artifacts are complete**
-      - After creating each artifact, re-run `openspec status --change "<name>" --json`
-      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
-      - Stop when all `applyRequires` artifacts are done
+   - After creating each artifact, re-run `openspec status --change "<name>" --json`
+   - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+   - Stop when all `applyRequires` artifacts are done
 
    c. **If an artifact requires user input** (unclear context):
-      - Use **AskUserQuestion tool** to clarify
-      - Then continue with creation
+   - Use **AskUserQuestion tool** to clarify
+   - Then continue with creation
 
 5. **Show final status**
    ```bash
@@ -78,6 +83,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 **Output**
 
 After completing all artifacts, summarize:
+
 - Change name and location
 - List of artifacts created with brief descriptions
 - What's ready: "All artifacts created! Ready for implementation."
@@ -94,6 +100,7 @@ After completing all artifacts, summarize:
   - These guide what you write, but should never appear in the output
 
 **Guardrails**
+
 - Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
 - Always read dependency artifacts before creating a new one
 - If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum

.agent/skills/openspec-new-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Start a new change using the experimental artifact-driven approach.
@@ -18,6 +18,7 @@ Start a new change using the experimental artifact-driven approach.
 1. **If no clear input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -35,24 +36,30 @@ Start a new change using the experimental artifact-driven approach.
    **Otherwise**: Omit `--schema` to use the default.
 
 3. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    Add `--schema <name>` only if the user requested a specific workflow.
    This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
 
 4. **Show the artifact status**
+
    ```bash
    openspec status --change "<name>"
    ```
+
    This shows which artifacts need to be created and which are ready (dependencies satisfied).
 
 5. **Get instructions for the first artifact**
    The first artifact depends on the schema (e.g., `proposal` for spec-driven).
    Check the status output to find the first artifact with status "ready".
+
    ```bash
    openspec instructions <first-artifact-id> --change "<name>"
    ```
+
    This outputs the template and context for creating the first artifact.
 
 6. **STOP and wait for user direction**
@@ -60,6 +67,7 @@ Start a new change using the experimental artifact-driven approach.
 **Output**
 
 After completing the steps, summarize:
+
 - Change name and location
 - Schema/workflow being used and its artifact sequence
 - Current status (0/N artifacts complete)
@@ -67,6 +75,7 @@ After completing the steps, summarize:
 - Prompt: "Ready to create the first artifact? Just describe what this change is about and I'll draft it, or ask me to continue."
 
 **Guardrails**
+
 - Do NOT create any artifacts yet - just show the instructions
 - Do NOT advance beyond showing the first artifact template
 - If the name is invalid (not kebab-case), ask for a valid name

.agent/skills/openspec-onboard/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
@@ -22,6 +22,7 @@ openspec status --json 2>&1 || echo "NOT_INITIALIZED"
 ```
 
 **If not initialized:**
+
 > OpenSpec isn't set up in this project yet. Run `openspec init` first, then come back to `/opsx:onboard`.
 
 Stop here if not initialized.
@@ -66,6 +67,7 @@ Scan the codebase for small improvement opportunities. Look for:
 6. **Missing validation** - User input handlers without validation
 
 Also check recent git activity:
+
 ```bash
 git log --oneline -10 2>/dev/null || echo "No git history"
 ```
@@ -101,6 +103,7 @@ Which task interests you? (Pick a number or describe your own)
 ```
 
 **If nothing found:** Fall back to asking what the user wants to build:
+
 > I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
 
 ### Scope Guardrail
@@ -133,6 +136,7 @@ Before we create a change, let me quickly show you **explore mode**—it's how y
 ```
 
 Spend 1-2 minutes investigating the relevant code:
+
 - Read the file(s) involved
 - Draw a quick ASCII diagram if it helps
 - Note any considerations
@@ -158,6 +162,7 @@ Now let's create a change to hold our work.
 ## Phase 4: Create the Change
 
 **EXPLAIN:**
+
 ```
 ## Creating a Change
 
@@ -167,21 +172,25 @@ Let me create one for our task.
 ```
 
 **DO:** Create the change with a derived kebab-case name:
+
 ```bash
 openspec new change "<derived-name>"
 ```
 
 **SHOW:**
+
 ```
 Created: `openspec/changes/<name>/`
 
 The folder structure:
 ```
+
 openspec/changes/<name>/
-├── proposal.md    ← Why we're doing this (empty, we'll fill it)
-├── design.md      ← How we'll build it (empty)
-├── specs/         ← Detailed requirements (empty)
-└── tasks.md       ← Implementation checklist (empty)
+├── proposal.md ← Why we're doing this (empty, we'll fill it)
+├── design.md ← How we'll build it (empty)
+├── specs/ ← Detailed requirements (empty)
+└── tasks.md ← Implementation checklist (empty)
+
 ```
 
 Now let's fill in the first artifact—the proposal.
@@ -192,6 +201,7 @@ Now let's fill in the first artifact—the proposal.
 ## Phase 5: Proposal
 
 **EXPLAIN:**
+
 ```
 ## The Proposal
 
@@ -236,9 +246,11 @@ Does this capture the intent? I can adjust before we save it.
 **PAUSE** - Wait for user approval/feedback.
 
 After approval, save the proposal:
+
 ```bash
 openspec instructions proposal --change "<name>" --json
 ```
+
 Then write the content to `openspec/changes/<name>/proposal.md`.
 
 ```
@@ -252,6 +264,7 @@ Next up: specs.
 ## Phase 6: Specs
 
 **EXPLAIN:**
+
 ```
 ## Specs
 
@@ -261,6 +274,7 @@ For a small task like this, we might only need one spec file.
 ```
 
 **DO:** Create the spec file:
+
 ```bash
 mkdir -p openspec/changes/<name>/specs/<capability-name>
 ```
@@ -296,6 +310,7 @@ Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
 ## Phase 7: Design
 
 **EXPLAIN:**
+
 ```
 ## Design
 
@@ -341,6 +356,7 @@ Save to `openspec/changes/<name>/design.md`.
 ## Phase 8: Tasks
 
 **EXPLAIN:**
+
 ```
 ## Tasks
 
@@ -379,6 +395,7 @@ Save to `openspec/changes/<name>/tasks.md`.
 ## Phase 9: Apply (Implementation)
 
 **EXPLAIN:**
+
 ```
 ## Implementation
 
@@ -413,6 +430,7 @@ The change is implemented! One more step—let's archive it.
 ## Phase 10: Archive
 
 **EXPLAIN:**
+
 ```
 ## Archiving
 
@@ -422,11 +440,13 @@ Archived changes become your project's decision history—you can always find th
 ```
 
 **DO:**
+
 ```bash
 openspec archive "<name>"
 ```
 
 **SHOW:**
+
 ```
 Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
 

.agent/skills/openspec-sync-specs/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Sync delta specs from a change to main specs.
@@ -47,28 +47,28 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 
    c. **Apply changes intelligently**:
 
-      **ADDED Requirements:**
-      - If requirement doesn't exist in main spec → add it
-      - If requirement already exists → update it to match (treat as implicit MODIFIED)
+   **ADDED Requirements:**
+   - If requirement doesn't exist in main spec → add it
+   - If requirement already exists → update it to match (treat as implicit MODIFIED)
 
-      **MODIFIED Requirements:**
-      - Find the requirement in main spec
-      - Apply the changes - this can be:
-        - Adding new scenarios (don't need to copy existing ones)
-        - Modifying existing scenarios
-        - Changing the requirement description
-      - Preserve scenarios/content not mentioned in the delta
+   **MODIFIED Requirements:**
+   - Find the requirement in main spec
+   - Apply the changes - this can be:
+     - Adding new scenarios (don't need to copy existing ones)
+     - Modifying existing scenarios
+     - Changing the requirement description
+   - Preserve scenarios/content not mentioned in the delta
 
-      **REMOVED Requirements:**
-      - Remove the entire requirement block from main spec
+   **REMOVED Requirements:**
+   - Remove the entire requirement block from main spec
 
-      **RENAMED Requirements:**
-      - Find the FROM requirement, rename to TO
+   **RENAMED Requirements:**
+   - Find the FROM requirement, rename to TO
 
    d. **Create new main spec** if capability doesn't exist yet:
-      - Create `openspec/specs/<capability>/spec.md`
-      - Add Purpose section (can be brief, mark as TBD)
-      - Add Requirements section with the ADDED requirements
+   - Create `openspec/specs/<capability>/spec.md`
+   - Add Purpose section (can be brief, mark as TBD)
+   - Add Requirements section with the ADDED requirements
 
 4. **Show summary**
 
@@ -82,16 +82,20 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 ## ADDED Requirements
 
 ### Requirement: New Feature
+
 The system SHALL do something new.
 
 #### Scenario: Basic case
+
 - **WHEN** user does X
 - **THEN** system does Y
 
 ## MODIFIED Requirements
 
 ### Requirement: Existing Feature
+
 #### Scenario: New scenario to add
+
 - **WHEN** user does A
 - **THEN** system does B
 
@@ -108,8 +112,9 @@ The system SHALL do something new.
 **Key Principle: Intelligent Merging**
 
 Unlike programmatic merging, you can apply **partial updates**:
+
 - To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
-- The delta represents *intent*, not a wholesale replacement
+- The delta represents _intent_, not a wholesale replacement
 - Use your judgment to merge changes sensibly
 
 **Output On Success**
@@ -131,6 +136,7 @@ Main specs are now updated. The change remains active - archive when implementat
 ```
 
 **Guardrails**
+
 - Read both delta and main specs before making changes
 - Preserve existing content not mentioned in delta
 - If something is unclear, ask for clarification

.agent/skills/openspec-verify-change/SKILL.md

@@ -5,8 +5,8 @@ license: MIT
 compatibility: Requires openspec CLI.
 metadata:
   author: openspec
-  version: "1.0"
-  generatedBy: "1.1.1"
+  version: '1.0'
+  generatedBy: '1.1.1'
 ---
 
 Verify that an implementation matches the change artifacts (specs, tasks, design).
@@ -26,9 +26,11 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
 2. **Check status to understand the schema**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand:
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifacts exist for this change
@@ -110,6 +112,7 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
 8. **Generate Verification Report**
 
    **Summary Scorecard**:
+
    ```
    ## Verification Report: <change-name>
 
@@ -122,7 +125,6 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
    ```
 
    **Issues by Priority**:
-
    1. **CRITICAL** (Must fix before archive):
       - Incomplete tasks
       - Missing requirement implementations
@@ -161,6 +163,7 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
 **Output Format**
 
 Use clear markdown with:
+
 - Table for summary scorecard
 - Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
 - Code references in format: `file.ts:123`

.agent/skills/project_overview/SKILL.md

@@ -1,13 +1,13 @@
 ---
-name: antigravity-manager
-description: Comprehensive guide to Antigravity Manager architecture, workflows, and development. Use this to understand how to work on the project.
+name: geminiNexus-manager
+description: Comprehensive guide to Gemini Nexus Manager architecture, workflows, and development. Use this to understand how to work on the project.
 ---
 
-# Antigravity Manager Developer Guide
+# Gemini Nexus Manager Developer Guide
 
 ## 🏗️ Architecture Overview
 
-Antigravity Manager is a hybrid Desktop Application built with Electron, React, and NestJS. It follows a modular architecture where the frontend (Renderer) communicates with the backend (Main) via type-safe IPC (ORPC).
+Gemini Nexus Manager is a hybrid Desktop Application built with Electron, React, and NestJS. It follows a modular architecture where the frontend (Renderer) communicates with the backend (Main) via type-safe IPC (ORPC).
 
 ```mermaid
 graph TD
@@ -69,7 +69,7 @@ The project uses `orpc` for type-safe communication.
 
 ### Database Access
 
-Data is stored in a local SQLite file (`test.db` in dev, user data in prod).
+Data is stored in a local SQLite file.
 
 - Use `Better-SQLite3` for direct access.
 - Logic should be encapsulated in `src/services` or `src/ipc`.

.agent/skills/ui-ux-pro-max/SKILL.md

@@ -2,6 +2,7 @@
 name: ui-ux-pro-max
 description: UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks.
 ---
+
 # ui-ux-pro-max
 
 Comprehensive design guide for web and mobile applications. Contains 67 styles, 96 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types across 13 technology stacks. Searchable database with priority-based recommendations.
@@ -17,16 +18,19 @@ python3 --version || python --version
 If Python is not installed, install it based on user's OS:
 
 **macOS:**
+
 ```bash
 brew install python3
 ```
 
 **Ubuntu/Debian:**
+
 ```bash
 sudo apt update && sudo apt install python3
 ```
 
 **Windows:**
+
 ```powershell
 winget install Python.Python.3.12
 ```
@@ -40,6 +44,7 @@ When user requests UI/UX work (design, build, create, implement, review, fix, im
 ### Step 1: Analyze User Requirements
 
 Extract key information from user request:
+
 - **Product type**: SaaS, e-commerce, portfolio, dashboard, landing page, etc.
 - **Style keywords**: minimal, playful, professional, elegant, dark mode, etc.
 - **Industry**: healthcare, fintech, gaming, education, etc.
@@ -54,12 +59,14 @@ python3 skills/ui-ux-pro-max/scripts/search.py "<product_type> <industry> <keywo
 ```
 
 This command:
+
 1. Searches 5 domains in parallel (product, style, color, landing, typography)
 2. Applies reasoning rules from `ui-reasoning.csv` to select best matches
 3. Returns complete design system: pattern, style, colors, typography, effects
 4. Includes anti-patterns to avoid
 
 **Example:**
+
 ```bash
 python3 skills/ui-ux-pro-max/scripts/search.py "beauty spa wellness service" --design-system -p "Serenity Spa"
 ```
@@ -73,18 +80,22 @@ python3 skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system --persi
 ```
 
 This creates:
+
 - `design-system/MASTER.md` — Global Source of Truth with all design rules
 - `design-system/pages/` — Folder for page-specific overrides
 
 **With page-specific override:**
+
 ```bash
 python3 skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system --persist -p "Project Name" --page "dashboard"
 ```
 
 This also creates:
+
 - `design-system/pages/dashboard.md` — Page-specific deviations from Master
 
 **How hierarchical retrieval works:**
+
 1. When building a specific page (e.g., "Checkout"), first check `design-system/pages/checkout.md`
 2. If the page file exists, its rules **override** the Master file
 3. If not, use `design-system/MASTER.md` exclusively
@@ -99,13 +110,13 @@ python3 skills/ui-ux-pro-max/scripts/search.py "<keyword>" --domain <domain> [-n
 
 **When to use detailed searches:**
 
-| Need | Domain | Example |
-|------|--------|---------|
-| More style options | `style` | `--domain style "glassmorphism dark"` |
-| Chart recommendations | `chart` | `--domain chart "real-time dashboard"` |
-| UX best practices | `ux` | `--domain ux "animation accessibility"` |
-| Alternative fonts | `typography` | `--domain typography "elegant luxury"` |
-| Landing structure | `landing` | `--domain landing "hero social-proof"` |
+| Need                  | Domain       | Example                                 |
+| --------------------- | ------------ | --------------------------------------- |
+| More style options    | `style`      | `--domain style "glassmorphism dark"`   |
+| Chart recommendations | `chart`      | `--domain chart "real-time dashboard"`  |
+| UX best practices     | `ux`         | `--domain ux "animation accessibility"` |
+| Alternative fonts     | `typography` | `--domain typography "elegant luxury"`  |
+| Landing structure     | `landing`    | `--domain landing "hero social-proof"`  |
 
 ### Step 4: Stack Guidelines (Default: html-tailwind)
 
@@ -123,32 +134,32 @@ Available stacks: `html-tailwind`, `react`, `nextjs`, `vue`, `svelte`, `swiftui`
 
 ### Available Domains
 
-| Domain | Use For | Example Keywords |
-|--------|---------|------------------|
-| `product` | Product type recommendations | SaaS, e-commerce, portfolio, healthcare, beauty, service |
-| `style` | UI styles, colors, effects | glassmorphism, minimalism, dark mode, brutalism |
-| `typography` | Font pairings, Google Fonts | elegant, playful, professional, modern |
-| `color` | Color palettes by product type | saas, ecommerce, healthcare, beauty, fintech, service |
-| `landing` | Page structure, CTA strategies | hero, hero-centric, testimonial, pricing, social-proof |
-| `chart` | Chart types, library recommendations | trend, comparison, timeline, funnel, pie |
-| `ux` | Best practices, anti-patterns | animation, accessibility, z-index, loading |
-| `react` | React/Next.js performance | waterfall, bundle, suspense, memo, rerender, cache |
-| `web` | Web interface guidelines | aria, focus, keyboard, semantic, virtualize |
-| `prompt` | AI prompts, CSS keywords | (style name) |
+| Domain       | Use For                              | Example Keywords                                         |
+| ------------ | ------------------------------------ | -------------------------------------------------------- |
+| `product`    | Product type recommendations         | SaaS, e-commerce, portfolio, healthcare, beauty, service |
+| `style`      | UI styles, colors, effects           | glassmorphism, minimalism, dark mode, brutalism          |
+| `typography` | Font pairings, Google Fonts          | elegant, playful, professional, modern                   |
+| `color`      | Color palettes by product type       | saas, ecommerce, healthcare, beauty, fintech, service    |
+| `landing`    | Page structure, CTA strategies       | hero, hero-centric, testimonial, pricing, social-proof   |
+| `chart`      | Chart types, library recommendations | trend, comparison, timeline, funnel, pie                 |
+| `ux`         | Best practices, anti-patterns        | animation, accessibility, z-index, loading               |
+| `react`      | React/Next.js performance            | waterfall, bundle, suspense, memo, rerender, cache       |
+| `web`        | Web interface guidelines             | aria, focus, keyboard, semantic, virtualize              |
+| `prompt`     | AI prompts, CSS keywords             | (style name)                                             |
 
 ### Available Stacks
 
-| Stack | Focus |
-|-------|-------|
-| `html-tailwind` | Tailwind utilities, responsive, a11y (DEFAULT) |
-| `react` | State, hooks, performance, patterns |
-| `nextjs` | SSR, routing, images, API routes |
-| `vue` | Composition API, Pinia, Vue Router |
-| `svelte` | Runes, stores, SvelteKit |
-| `swiftui` | Views, State, Navigation, Animation |
-| `react-native` | Components, Navigation, Lists |
-| `flutter` | Widgets, State, Layout, Theming |
-| `shadcn` | shadcn/ui components, theming, forms, patterns |
+| Stack             | Focus                                                 |
+| ----------------- | ----------------------------------------------------- |
+| `html-tailwind`   | Tailwind utilities, responsive, a11y (DEFAULT)        |
+| `react`           | State, hooks, performance, patterns                   |
+| `nextjs`          | SSR, routing, images, API routes                      |
+| `vue`             | Composition API, Pinia, Vue Router                    |
+| `svelte`          | Runes, stores, SvelteKit                              |
+| `swiftui`         | Views, State, Navigation, Animation                   |
+| `react-native`    | Components, Navigation, Lists                         |
+| `flutter`         | Widgets, State, Layout, Theming                       |
+| `shadcn`          | shadcn/ui components, theming, forms, patterns        |
 | `jetpack-compose` | Composables, Modifiers, State Hoisting, Recomposition |
 
 ---
@@ -158,6 +169,7 @@ Available stacks: `html-tailwind`, `react`, `nextjs`, `vue`, `svelte`, `swiftui`
 **User request:** "Làm landing page cho dịch vụ chăm sóc da chuyên nghiệp"
 
 ### Step 1: Analyze Requirements
+
 - Product type: Beauty/Spa service
 - Style keywords: elegant, professional, soft
 - Industry: Beauty/Wellness
@@ -222,37 +234,37 @@ These are frequently overlooked issues that make UI look unprofessional:
 
 ### Icons & Visual Elements
 
-| Rule | Do | Don't |
-|------|----|----- |
-| **No emoji icons** | Use SVG icons (Heroicons, Lucide, Simple Icons) | Use emojis like 🎨 🚀 ⚙️ as UI icons |
-| **Stable hover states** | Use color/opacity transitions on hover | Use scale transforms that shift layout |
-| **Correct brand logos** | Research official SVG from Simple Icons | Guess or use incorrect logo paths |
-| **Consistent icon sizing** | Use fixed viewBox (24x24) with w-6 h-6 | Mix different icon sizes randomly |
+| Rule                       | Do                                              | Don't                                  |
+| -------------------------- | ----------------------------------------------- | -------------------------------------- |
+| **No emoji icons**         | Use SVG icons (Heroicons, Lucide, Simple Icons) | Use emojis like 🎨 🚀 ⚙️ as UI icons   |
+| **Stable hover states**    | Use color/opacity transitions on hover          | Use scale transforms that shift layout |
+| **Correct brand logos**    | Research official SVG from Simple Icons         | Guess or use incorrect logo paths      |
+| **Consistent icon sizing** | Use fixed viewBox (24x24) with w-6 h-6          | Mix different icon sizes randomly      |
 
 ### Interaction & Cursor
 
-| Rule | Do | Don't |
-|------|----|----- |
-| **Cursor pointer** | Add `cursor-pointer` to all clickable/hoverable cards | Leave default cursor on interactive elements |
-| **Hover feedback** | Provide visual feedback (color, shadow, border) | No indication element is interactive |
-| **Smooth transitions** | Use `transition-colors duration-200` | Instant state changes or too slow (>500ms) |
+| Rule                   | Do                                                    | Don't                                        |
+| ---------------------- | ----------------------------------------------------- | -------------------------------------------- |
+| **Cursor pointer**     | Add `cursor-pointer` to all clickable/hoverable cards | Leave default cursor on interactive elements |
+| **Hover feedback**     | Provide visual feedback (color, shadow, border)       | No indication element is interactive         |
+| **Smooth transitions** | Use `transition-colors duration-200`                  | Instant state changes or too slow (>500ms)   |
 
 ### Light/Dark Mode Contrast
 
-| Rule | Do | Don't |
-|------|----|----- |
-| **Glass card light mode** | Use `bg-white/80` or higher opacity | Use `bg-white/10` (too transparent) |
-| **Text contrast light** | Use `#0F172A` (slate-900) for text | Use `#94A3B8` (slate-400) for body text |
-| **Muted text light** | Use `#475569` (slate-600) minimum | Use gray-400 or lighter |
-| **Border visibility** | Use `border-gray-200` in light mode | Use `border-white/10` (invisible) |
+| Rule                      | Do                                  | Don't                                   |
+| ------------------------- | ----------------------------------- | --------------------------------------- |
+| **Glass card light mode** | Use `bg-white/80` or higher opacity | Use `bg-white/10` (too transparent)     |
+| **Text contrast light**   | Use `#0F172A` (slate-900) for text  | Use `#94A3B8` (slate-400) for body text |
+| **Muted text light**      | Use `#475569` (slate-600) minimum   | Use gray-400 or lighter                 |
+| **Border visibility**     | Use `border-gray-200` in light mode | Use `border-white/10` (invisible)       |
 
 ### Layout & Spacing
 
-| Rule | Do | Don't |
-|------|----|----- |
-| **Floating navbar** | Add `top-4 left-4 right-4` spacing | Stick navbar to `top-0 left-0 right-0` |
-| **Content padding** | Account for fixed navbar height | Let content hide behind fixed elements |
-| **Consistent max-width** | Use same `max-w-6xl` or `max-w-7xl` | Mix different container widths |
+| Rule                     | Do                                  | Don't                                  |
+| ------------------------ | ----------------------------------- | -------------------------------------- |
+| **Floating navbar**      | Add `top-4 left-4 right-4` spacing  | Stick navbar to `top-0 left-0 right-0` |
+| **Content padding**      | Account for fixed navbar height     | Let content hide behind fixed elements |
+| **Consistent max-width** | Use same `max-w-6xl` or `max-w-7xl` | Mix different container widths         |
 
 ---
 
@@ -261,6 +273,7 @@ These are frequently overlooked issues that make UI look unprofessional:
 Before delivering UI code, verify these items:
 
 ### Visual Quality
+
 - [ ] No emojis used as icons (use SVG instead)
 - [ ] All icons from consistent icon set (Heroicons/Lucide)
 - [ ] Brand logos are correct (verified from Simple Icons)
@@ -268,24 +281,28 @@ Before delivering UI code, verify these items:
 - [ ] Use theme colors directly (bg-primary) not var() wrapper
 
 ### Interaction
+
 - [ ] All clickable elements have `cursor-pointer`
 - [ ] Hover states provide clear visual feedback
 - [ ] Transitions are smooth (150-300ms)
 - [ ] Focus states visible for keyboard navigation
 
 ### Light/Dark Mode
+
 - [ ] Light mode text has sufficient contrast (4.5:1 minimum)
 - [ ] Glass/transparent elements visible in light mode
 - [ ] Borders visible in both modes
 - [ ] Test both modes before delivery
 
 ### Layout
+
 - [ ] Floating elements have proper spacing from edges
 - [ ] No content hidden behind fixed navbars
 - [ ] Responsive at 375px, 768px, 1024px, 1440px
 - [ ] No horizontal scroll on mobile
 
 ### Accessibility
+
 - [ ] All images have alt text
 - [ ] Form inputs have labels
 - [ ] Color is not the only indicator

.agent/skills/vercel-composition-patterns/AGENTS.md

@@ -73,16 +73,10 @@ function Composer({
       ) : isThread ? (
         <AlsoSendToChannelField id={channelId} />
       ) : null}
-      {isEditing ? (
-        <EditActions />
-      ) : isForwarding ? (
-        <ForwardActions />
-      ) : (
-        <DefaultActions />
-      )}
+      {isEditing ? <EditActions /> : isForwarding ? <ForwardActions /> : <DefaultActions />}
       <Footer onSubmit={onSubmit} />
     </form>
-  )
+  );
 }
 ```
 
@@ -102,7 +96,7 @@ function ChannelComposer() {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Thread composer - adds "also send to channel" field
@@ -118,7 +112,7 @@ function ThreadComposer({ channelId }: { channelId: string }) {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Edit composer - different footer actions
@@ -133,7 +127,7 @@ function EditComposer() {
         <Composer.SaveEdit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 ```
 
@@ -177,25 +171,21 @@ function Composer({
         </Footer>
       )}
     </form>
-  )
+  );
 }
 ```
 
 **Correct: compound components with shared context**
 
 ```tsx
-const ComposerContext = createContext<ComposerContextValue | null>(null)
+const ComposerContext = createContext<ComposerContextValue | null>(null);
 
 function ComposerProvider({ children, state, actions, meta }: ProviderProps) {
-  return (
-    <ComposerContext value={{ state, actions, meta }}>
-      {children}
-    </ComposerContext>
-  )
+  return <ComposerContext value={{ state, actions, meta }}>{children}</ComposerContext>;
 }
 
 function ComposerFrame({ children }: { children: React.ReactNode }) {
-  return <form>{children}</form>
+  return <form>{children}</form>;
 }
 
 function ComposerInput() {
@@ -203,21 +193,21 @@ function ComposerInput() {
     state,
     actions: { update },
     meta: { inputRef },
-  } = use(ComposerContext)
+  } = use(ComposerContext);
   return (
     <TextInput
       ref={inputRef}
       value={state.input}
       onChangeText={(text) => update((s) => ({ ...s, input: text }))}
     />
-  )
+  );
 }
 
 function ComposerSubmit() {
   const {
     actions: { submit },
-  } = use(ComposerContext)
-  return <Button onPress={submit}>Send</Button>
+  } = use(ComposerContext);
+  return <Button onPress={submit}>Send</Button>;
 }
 
 // Export as compound component
@@ -231,7 +221,7 @@ const Composer = {
   Attachments: ComposerAttachments,
   Formatting: ComposerFormatting,
   Emojis: ComposerEmojis,
-}
+};
 ```
 
 **Usage:**
@@ -275,18 +265,15 @@ useState, Zustand, or a server sync.
 ```tsx
 function ChannelComposer({ channelId }: { channelId: string }) {
   // UI component knows about global state implementation
-  const state = useGlobalChannelState(channelId)
-  const { submit, updateInput } = useChannelSync(channelId)
+  const state = useGlobalChannelState(channelId);
+  const { submit, updateInput } = useChannelSync(channelId);
 
   return (
     <Composer.Frame>
-      <Composer.Input
-        value={state.input}
-        onChange={(text) => sync.updateInput(text)}
-      />
+      <Composer.Input value={state.input} onChange={(text) => sync.updateInput(text)} />
       <Composer.Submit onPress={() => sync.submit()} />
     </Composer.Frame>
-  )
+  );
 }
 ```
 
@@ -298,21 +285,17 @@ function ChannelProvider({
   channelId,
   children,
 }: {
-  channelId: string
-  children: React.ReactNode
+  channelId: string;
+  children: React.ReactNode;
 }) {
-  const { state, update, submit } = useGlobalChannel(channelId)
-  const inputRef = useRef(null)
+  const { state, update, submit } = useGlobalChannel(channelId);
+  const inputRef = useRef(null);
 
   return (
-    <Composer.Provider
-      state={state}
-      actions={{ update, submit }}
-      meta={{ inputRef }}
-    >
+    <Composer.Provider state={state} actions={{ update, submit }} meta={{ inputRef }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 // UI component only knows about the context interface
@@ -325,7 +308,7 @@ function ChannelComposer() {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Usage
@@ -334,7 +317,7 @@ function Channel({ channelId }: { channelId: string }) {
     <ChannelProvider channelId={channelId}>
       <ChannelComposer />
     </ChannelProvider>
-  )
+  );
 }
 ```
 
@@ -343,28 +326,25 @@ function Channel({ channelId }: { channelId: string }) {
 ```tsx
 // Local state for ephemeral forms
 function ForwardMessageProvider({ children }) {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
 
   return (
-    <Composer.Provider
-      state={state}
-      actions={{ update: setState, submit: forwardMessage }}
-    >
+    <Composer.Provider state={state} actions={{ update: setState, submit: forwardMessage }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 // Global synced state for channels
 function ChannelProvider({ channelId, children }) {
-  const { state, update, submit } = useGlobalChannel(channelId)
+  const { state, update, submit } = useGlobalChannel(channelId);
 
   return (
     <Composer.Provider state={state} actions={{ update, submit }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 ```
 
@@ -393,8 +373,8 @@ dependency-injectable.
 ```tsx
 function ComposerInput() {
   // Tightly coupled to a specific hook
-  const { input, setInput } = useChannelComposerState()
-  return <TextInput value={input} onChangeText={setInput} />
+  const { input, setInput } = useChannelComposerState();
+  return <TextInput value={input} onChangeText={setInput} />;
 }
 ```
 
@@ -403,27 +383,27 @@ function ComposerInput() {
 ```tsx
 // Define a GENERIC interface that any provider can implement
 interface ComposerState {
-  input: string
-  attachments: Attachment[]
-  isSubmitting: boolean
+  input: string;
+  attachments: Attachment[];
+  isSubmitting: boolean;
 }
 
 interface ComposerActions {
-  update: (updater: (state: ComposerState) => ComposerState) => void
-  submit: () => void
+  update: (updater: (state: ComposerState) => ComposerState) => void;
+  submit: () => void;
 }
 
 interface ComposerMeta {
-  inputRef: React.RefObject<TextInput>
+  inputRef: React.RefObject<TextInput>;
 }
 
 interface ComposerContextValue {
-  state: ComposerState
-  actions: ComposerActions
-  meta: ComposerMeta
+  state: ComposerState;
+  actions: ComposerActions;
+  meta: ComposerMeta;
 }
 
-const ComposerContext = createContext<ComposerContextValue | null>(null)
+const ComposerContext = createContext<ComposerContextValue | null>(null);
 ```
 
 **UI components consume the interface, not the implementation:**
@@ -434,7 +414,7 @@ function ComposerInput() {
     state,
     actions: { update },
     meta,
-  } = use(ComposerContext)
+  } = use(ComposerContext);
 
   // This component works with ANY provider that implements the interface
   return (
@@ -443,7 +423,7 @@ function ComposerInput() {
       value={state.input}
       onChangeText={(text) => update((s) => ({ ...s, input: text }))}
     />
-  )
+  );
 }
 ```
 
@@ -452,9 +432,9 @@ function ComposerInput() {
 ```tsx
 // Provider A: Local state for ephemeral forms
 function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
-  const [state, setState] = useState(initialState)
-  const inputRef = useRef(null)
-  const submit = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const inputRef = useRef(null);
+  const submit = useForwardMessage();
 
   return (
     <ComposerContext
@@ -466,13 +446,13 @@ function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
     >
       {children}
     </ComposerContext>
-  )
+  );
 }
 
 // Provider B: Global synced state for channels
 function ChannelProvider({ channelId, children }: Props) {
-  const { state, update, submit } = useGlobalChannel(channelId)
-  const inputRef = useRef(null)
+  const { state, update, submit } = useGlobalChannel(channelId);
+  const inputRef = useRef(null);
 
   return (
     <ComposerContext
@@ -484,7 +464,7 @@ function ChannelProvider({ channelId, children }: Props) {
     >
       {children}
     </ComposerContext>
-  )
+  );
 }
 ```
 
@@ -534,21 +514,21 @@ function ForwardMessageDialog() {
         </DialogActions>
       </Dialog>
     </ForwardMessageProvider>
-  )
+  );
 }
 
 // This button lives OUTSIDE Composer.Frame but can still submit based on its context!
 function ForwardButton() {
   const {
     actions: { submit },
-  } = use(ComposerContext)
-  return <Button onPress={submit}>Forward</Button>
+  } = use(ComposerContext);
+  return <Button onPress={submit}>Forward</Button>;
 }
 
 // This preview lives OUTSIDE Composer.Frame but can read composer's state!
 function MessagePreview() {
-  const { state } = use(ComposerContext)
-  return <Preview message={state.input} attachments={state.attachments} />
+  const { state } = use(ComposerContext);
+  return <Preview message={state.input} attachments={state.attachments} />;
 }
 ```
 
@@ -582,15 +562,15 @@ or awkward refs.
 
 ```tsx
 function ForwardMessageComposer() {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
 
   return (
     <Composer.Frame>
       <Composer.Input />
       <Composer.Footer />
     </Composer.Frame>
-  )
+  );
 }
 
 // Problem: How does this button access composer state?
@@ -604,7 +584,7 @@ function ForwardMessageDialog() {
         <ForwardButton /> {/* Needs to call submit */}
       </DialogActions>
     </Dialog>
-  )
+  );
 }
 ```
 
@@ -612,20 +592,20 @@ function ForwardMessageDialog() {
 
 ```tsx
 function ForwardMessageDialog() {
-  const [input, setInput] = useState('')
+  const [input, setInput] = useState('');
   return (
     <Dialog>
       <ForwardMessageComposer onInputChange={setInput} />
       <MessagePreview input={input} />
     </Dialog>
-  )
+  );
 }
 
 function ForwardMessageComposer({ onInputChange }) {
-  const [state, setState] = useState(initialState)
+  const [state, setState] = useState(initialState);
   useEffect(() => {
-    onInputChange(state.input) // Sync on every change 😬
-  }, [state.input])
+    onInputChange(state.input); // Sync on every change 😬
+  }, [state.input]);
 }
 ```
 
@@ -633,13 +613,13 @@ function ForwardMessageComposer({ onInputChange }) {
 
 ```tsx
 function ForwardMessageDialog() {
-  const stateRef = useRef(null)
+  const stateRef = useRef(null);
   return (
     <Dialog>
       <ForwardMessageComposer stateRef={stateRef} />
       <ForwardButton onPress={() => submit(stateRef.current)} />
     </Dialog>
-  )
+  );
 }
 ```
 
@@ -647,9 +627,9 @@ function ForwardMessageDialog() {
 
 ```tsx
 function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
-  const inputRef = useRef(null)
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
+  const inputRef = useRef(null);
 
   return (
     <Composer.Provider
@@ -659,7 +639,7 @@ function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
     >
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 function ForwardMessageDialog() {
@@ -674,12 +654,12 @@ function ForwardMessageDialog() {
         </DialogActions>
       </Dialog>
     </ForwardMessageProvider>
-  )
+  );
 }
 
 function ForwardButton() {
-  const { actions } = use(Composer.Context)
-  return <Button onPress={actions.submit}>Forward</Button>
+  const { actions } = use(Composer.Context);
+  return <Button onPress={actions.submit}>Forward</Button>;
 }
 ```
 
@@ -718,13 +698,7 @@ itself.
 
 ```tsx
 // What does this component actually render?
-<Composer
-  isThread
-  isEditing={false}
-  channelId='abc'
-  showAttachments
-  showFormatting={false}
-/>
+<Composer isThread isEditing={false} channelId="abc" showAttachments showFormatting={false} />
 ```
 
 **Correct: explicit variants**
@@ -760,7 +734,7 @@ function ThreadComposer({ channelId }: { channelId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </ThreadProvider>
-  )
+  );
 }
 
 function EditMessageComposer({ messageId }: { messageId: string }) {
@@ -776,7 +750,7 @@ function EditMessageComposer({ messageId }: { messageId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </EditMessageProvider>
-  )
+  );
 }
 
 function ForwardMessageComposer({ messageId }: { messageId: string }) {
@@ -791,7 +765,7 @@ function ForwardMessageComposer({ messageId }: { messageId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </ForwardMessageProvider>
-  )
+  );
 }
 ```
 
@@ -823,9 +797,9 @@ function Composer({
   renderFooter,
   renderActions,
 }: {
-  renderHeader?: () => React.ReactNode
-  renderFooter?: () => React.ReactNode
-  renderActions?: () => React.ReactNode
+  renderHeader?: () => React.ReactNode;
+  renderFooter?: () => React.ReactNode;
+  renderActions?: () => React.ReactNode;
 }) {
   return (
     <form>
@@ -834,7 +808,7 @@ function Composer({
       {renderFooter ? renderFooter() : <DefaultFooter />}
       {renderActions?.()}
     </form>
-  )
+  );
 }
 
 // Usage is awkward and inflexible
@@ -849,18 +823,18 @@ return (
     )}
     renderActions={() => <SubmitButton />}
   />
-)
+);
 ```
 
 **Correct: compound components with children**
 
 ```tsx
 function ComposerFrame({ children }: { children: React.ReactNode }) {
-  return <form>{children}</form>
+  return <form>{children}</form>;
 }
 
 function ComposerFooter({ children }: { children: React.ReactNode }) {
-  return <footer className='flex'>{children}</footer>
+  return <footer className="flex">{children}</footer>;
 }
 
 // Usage is flexible
@@ -874,17 +848,14 @@ return (
       <SubmitButton />
     </Composer.Footer>
   </Composer.Frame>
-)
+);
 ```
 
 **When render props are appropriate:**
 
 ```tsx
 // Render props work well when you need to pass data back
-<List
-  data={items}
-  renderItem={({ item, index }) => <Item item={item} index={index} />}
-/>
+<List data={items} renderItem={({ item, index }) => <Item item={item} index={index} />} />
 ```
 
 Use render props when the parent needs to provide data or state to the child.
@@ -911,28 +882,28 @@ In React 19, `ref` is now a regular prop (no `forwardRef` wrapper needed), and `
 
 ```tsx
 const ComposerInput = forwardRef<TextInput, Props>((props, ref) => {
-  return <TextInput ref={ref} {...props} />
-})
+  return <TextInput ref={ref} {...props} />;
+});
 ```
 
 **Correct: ref as a regular prop**
 
 ```tsx
 function ComposerInput({ ref, ...props }: Props & { ref?: React.Ref<TextInput> }) {
-  return <TextInput ref={ref} {...props} />
+  return <TextInput ref={ref} {...props} />;
 }
 ```
 
 **Incorrect: useContext in React 19**
 
 ```tsx
-const value = useContext(MyContext)
+const value = useContext(MyContext);
 ```
 
 **Correct: use instead of useContext**
 
 ```tsx
-const value = use(MyContext)
+const value = use(MyContext);
 ```
 
 `use()` can also be called conditionally, unlike `useContext()`.

.agent/skills/vercel-composition-patterns/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: vercel-composition-patterns
-description:
-  React composition patterns that scale. Use when refactoring components with
+description: React composition patterns that scale. Use when refactoring components with
   boolean prop proliferation, building flexible component libraries, or
   designing reusable APIs. Triggers on tasks involving compound components,
   render props, context providers, or component architecture. Includes React 19

.agent/skills/vercel-composition-patterns/rules/architecture-avoid-boolean-props.md

@@ -32,16 +32,10 @@ function Composer({
       ) : isThread ? (
         <AlsoSendToChannelField id={channelId} />
       ) : null}
-      {isEditing ? (
-        <EditActions />
-      ) : isForwarding ? (
-        <ForwardActions />
-      ) : (
-        <DefaultActions />
-      )}
+      {isEditing ? <EditActions /> : isForwarding ? <ForwardActions /> : <DefaultActions />}
       <Footer onSubmit={onSubmit} />
     </form>
-  )
+  );
 }
 ```
 
@@ -61,7 +55,7 @@ function ChannelComposer() {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Thread composer - adds "also send to channel" field
@@ -77,7 +71,7 @@ function ThreadComposer({ channelId }: { channelId: string }) {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Edit composer - different footer actions
@@ -92,7 +86,7 @@ function EditComposer() {
         <Composer.SaveEdit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-composition-patterns/rules/architecture-compound-components.md

@@ -37,25 +37,21 @@ function Composer({
         </Footer>
       )}
     </form>
-  )
+  );
 }
 ```
 
 **Correct (compound components with shared context):**
 
 ```tsx
-const ComposerContext = createContext<ComposerContextValue | null>(null)
+const ComposerContext = createContext<ComposerContextValue | null>(null);
 
 function ComposerProvider({ children, state, actions, meta }: ProviderProps) {
-  return (
-    <ComposerContext value={{ state, actions, meta }}>
-      {children}
-    </ComposerContext>
-  )
+  return <ComposerContext value={{ state, actions, meta }}>{children}</ComposerContext>;
 }
 
 function ComposerFrame({ children }: { children: React.ReactNode }) {
-  return <form>{children}</form>
+  return <form>{children}</form>;
 }
 
 function ComposerInput() {
@@ -63,21 +59,21 @@ function ComposerInput() {
     state,
     actions: { update },
     meta: { inputRef },
-  } = use(ComposerContext)
+  } = use(ComposerContext);
   return (
     <TextInput
       ref={inputRef}
       value={state.input}
       onChangeText={(text) => update((s) => ({ ...s, input: text }))}
     />
-  )
+  );
 }
 
 function ComposerSubmit() {
   const {
     actions: { submit },
-  } = use(ComposerContext)
-  return <Button onPress={submit}>Send</Button>
+  } = use(ComposerContext);
+  return <Button onPress={submit}>Send</Button>;
 }
 
 // Export as compound component
@@ -91,7 +87,7 @@ const Composer = {
   Attachments: ComposerAttachments,
   Formatting: ComposerFormatting,
   Emojis: ComposerEmojis,
-}
+};
 ```
 
 **Usage:**

.agent/skills/vercel-composition-patterns/rules/patterns-children-over-render-props.md

@@ -19,9 +19,9 @@ function Composer({
   renderFooter,
   renderActions,
 }: {
-  renderHeader?: () => React.ReactNode
-  renderFooter?: () => React.ReactNode
-  renderActions?: () => React.ReactNode
+  renderHeader?: () => React.ReactNode;
+  renderFooter?: () => React.ReactNode;
+  renderActions?: () => React.ReactNode;
 }) {
   return (
     <form>
@@ -30,7 +30,7 @@ function Composer({
       {renderFooter ? renderFooter() : <DefaultFooter />}
       {renderActions?.()}
     </form>
-  )
+  );
 }
 
 // Usage is awkward and inflexible
@@ -45,18 +45,18 @@ return (
     )}
     renderActions={() => <SubmitButton />}
   />
-)
+);
 ```
 
 **Correct (compound components with children):**
 
 ```tsx
 function ComposerFrame({ children }: { children: React.ReactNode }) {
-  return <form>{children}</form>
+  return <form>{children}</form>;
 }
 
 function ComposerFooter({ children }: { children: React.ReactNode }) {
-  return <footer className='flex'>{children}</footer>
+  return <footer className="flex">{children}</footer>;
 }
 
 // Usage is flexible
@@ -70,17 +70,14 @@ return (
       <SubmitButton />
     </Composer.Footer>
   </Composer.Frame>
-)
+);
 ```
 
 **When render props are appropriate:**
 
 ```tsx
 // Render props work well when you need to pass data back
-<List
-  data={items}
-  renderItem={({ item, index }) => <Item item={item} index={index} />}
-/>
+<List data={items} renderItem={({ item, index }) => <Item item={item} index={index} />} />
 ```
 
 Use render props when the parent needs to provide data or state to the child.

.agent/skills/vercel-composition-patterns/rules/patterns-explicit-variants.md

@@ -15,13 +15,7 @@ itself.
 
 ```tsx
 // What does this component actually render?
-<Composer
-  isThread
-  isEditing={false}
-  channelId='abc'
-  showAttachments
-  showFormatting={false}
-/>
+<Composer isThread isEditing={false} channelId="abc" showAttachments showFormatting={false} />
 ```
 
 **Correct (explicit variants):**
@@ -56,7 +50,7 @@ function ThreadComposer({ channelId }: { channelId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </ThreadProvider>
-  )
+  );
 }
 
 function EditMessageComposer({ messageId }: { messageId: string }) {
@@ -72,7 +66,7 @@ function EditMessageComposer({ messageId }: { messageId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </EditMessageProvider>
-  )
+  );
 }
 
 function ForwardMessageComposer({ messageId }: { messageId: string }) {
@@ -87,7 +81,7 @@ function ForwardMessageComposer({ messageId }: { messageId: string }) {
         </Composer.Footer>
       </Composer.Frame>
     </ForwardMessageProvider>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-composition-patterns/rules/react19-no-forwardref.md

@@ -15,28 +15,28 @@ In React 19, `ref` is now a regular prop (no `forwardRef` wrapper needed), and `
 
 ```tsx
 const ComposerInput = forwardRef<TextInput, Props>((props, ref) => {
-  return <TextInput ref={ref} {...props} />
-})
+  return <TextInput ref={ref} {...props} />;
+});
 ```
 
 **Correct (ref as a regular prop):**
 
 ```tsx
 function ComposerInput({ ref, ...props }: Props & { ref?: React.Ref<TextInput> }) {
-  return <TextInput ref={ref} {...props} />
+  return <TextInput ref={ref} {...props} />;
 }
 ```
 
 **Incorrect (useContext in React 19):**
 
 ```tsx
-const value = useContext(MyContext)
+const value = useContext(MyContext);
 ```
 
 **Correct (use instead of useContext):**
 
 ```tsx
-const value = use(MyContext)
+const value = use(MyContext);
 ```
 
 `use()` can also be called conditionally, unlike `useContext()`.

.agent/skills/vercel-composition-patterns/rules/state-context-interface.md

@@ -20,8 +20,8 @@ dependency-injectable.
 ```tsx
 function ComposerInput() {
   // Tightly coupled to a specific hook
-  const { input, setInput } = useChannelComposerState()
-  return <TextInput value={input} onChangeText={setInput} />
+  const { input, setInput } = useChannelComposerState();
+  return <TextInput value={input} onChangeText={setInput} />;
 }
 ```
 
@@ -30,27 +30,27 @@ function ComposerInput() {
 ```tsx
 // Define a GENERIC interface that any provider can implement
 interface ComposerState {
-  input: string
-  attachments: Attachment[]
-  isSubmitting: boolean
+  input: string;
+  attachments: Attachment[];
+  isSubmitting: boolean;
 }
 
 interface ComposerActions {
-  update: (updater: (state: ComposerState) => ComposerState) => void
-  submit: () => void
+  update: (updater: (state: ComposerState) => ComposerState) => void;
+  submit: () => void;
 }
 
 interface ComposerMeta {
-  inputRef: React.RefObject<TextInput>
+  inputRef: React.RefObject<TextInput>;
 }
 
 interface ComposerContextValue {
-  state: ComposerState
-  actions: ComposerActions
-  meta: ComposerMeta
+  state: ComposerState;
+  actions: ComposerActions;
+  meta: ComposerMeta;
 }
 
-const ComposerContext = createContext<ComposerContextValue | null>(null)
+const ComposerContext = createContext<ComposerContextValue | null>(null);
 ```
 
 **UI components consume the interface, not the implementation:**
@@ -61,7 +61,7 @@ function ComposerInput() {
     state,
     actions: { update },
     meta,
-  } = use(ComposerContext)
+  } = use(ComposerContext);
 
   // This component works with ANY provider that implements the interface
   return (
@@ -70,7 +70,7 @@ function ComposerInput() {
       value={state.input}
       onChangeText={(text) => update((s) => ({ ...s, input: text }))}
     />
-  )
+  );
 }
 ```
 
@@ -79,9 +79,9 @@ function ComposerInput() {
 ```tsx
 // Provider A: Local state for ephemeral forms
 function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
-  const [state, setState] = useState(initialState)
-  const inputRef = useRef(null)
-  const submit = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const inputRef = useRef(null);
+  const submit = useForwardMessage();
 
   return (
     <ComposerContext
@@ -93,13 +93,13 @@ function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
     >
       {children}
     </ComposerContext>
-  )
+  );
 }
 
 // Provider B: Global synced state for channels
 function ChannelProvider({ channelId, children }: Props) {
-  const { state, update, submit } = useGlobalChannel(channelId)
-  const inputRef = useRef(null)
+  const { state, update, submit } = useGlobalChannel(channelId);
+  const inputRef = useRef(null);
 
   return (
     <ComposerContext
@@ -111,7 +111,7 @@ function ChannelProvider({ channelId, children }: Props) {
     >
       {children}
     </ComposerContext>
-  )
+  );
 }
 ```
 
@@ -165,21 +165,21 @@ function ForwardMessageDialog() {
         </DialogActions>
       </Dialog>
     </ForwardMessageProvider>
-  )
+  );
 }
 
 // This button lives OUTSIDE Composer.Frame but can still submit based on its context!
 function ForwardButton() {
   const {
     actions: { submit },
-  } = use(ComposerContext)
-  return <Button onPress={submit}>Forward</Button>
+  } = use(ComposerContext);
+  return <Button onPress={submit}>Forward</Button>;
 }
 
 // This preview lives OUTSIDE Composer.Frame but can read composer's state!
 function MessagePreview() {
-  const { state } = use(ComposerContext)
-  return <Preview message={state.input} attachments={state.attachments} />
+  const { state } = use(ComposerContext);
+  return <Preview message={state.input} attachments={state.attachments} />;
 }
 ```
 

.agent/skills/vercel-composition-patterns/rules/state-decouple-implementation.md

@@ -16,18 +16,15 @@ useState, Zustand, or a server sync.
 ```tsx
 function ChannelComposer({ channelId }: { channelId: string }) {
   // UI component knows about global state implementation
-  const state = useGlobalChannelState(channelId)
-  const { submit, updateInput } = useChannelSync(channelId)
+  const state = useGlobalChannelState(channelId);
+  const { submit, updateInput } = useChannelSync(channelId);
 
   return (
     <Composer.Frame>
-      <Composer.Input
-        value={state.input}
-        onChange={(text) => sync.updateInput(text)}
-      />
+      <Composer.Input value={state.input} onChange={(text) => sync.updateInput(text)} />
       <Composer.Submit onPress={() => sync.submit()} />
     </Composer.Frame>
-  )
+  );
 }
 ```
 
@@ -39,21 +36,17 @@ function ChannelProvider({
   channelId,
   children,
 }: {
-  channelId: string
-  children: React.ReactNode
+  channelId: string;
+  children: React.ReactNode;
 }) {
-  const { state, update, submit } = useGlobalChannel(channelId)
-  const inputRef = useRef(null)
+  const { state, update, submit } = useGlobalChannel(channelId);
+  const inputRef = useRef(null);
 
   return (
-    <Composer.Provider
-      state={state}
-      actions={{ update, submit }}
-      meta={{ inputRef }}
-    >
+    <Composer.Provider state={state} actions={{ update, submit }} meta={{ inputRef }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 // UI component only knows about the context interface
@@ -66,7 +59,7 @@ function ChannelComposer() {
         <Composer.Submit />
       </Composer.Footer>
     </Composer.Frame>
-  )
+  );
 }
 
 // Usage
@@ -75,7 +68,7 @@ function Channel({ channelId }: { channelId: string }) {
     <ChannelProvider channelId={channelId}>
       <ChannelComposer />
     </ChannelProvider>
-  )
+  );
 }
 ```
 
@@ -84,28 +77,25 @@ function Channel({ channelId }: { channelId: string }) {
 ```tsx
 // Local state for ephemeral forms
 function ForwardMessageProvider({ children }) {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
 
   return (
-    <Composer.Provider
-      state={state}
-      actions={{ update: setState, submit: forwardMessage }}
-    >
+    <Composer.Provider state={state} actions={{ update: setState, submit: forwardMessage }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 // Global synced state for channels
 function ChannelProvider({ channelId, children }) {
-  const { state, update, submit } = useGlobalChannel(channelId)
+  const { state, update, submit } = useGlobalChannel(channelId);
 
   return (
     <Composer.Provider state={state} actions={{ update, submit }}>
       {children}
     </Composer.Provider>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-composition-patterns/rules/state-lift-state.md

@@ -15,15 +15,15 @@ or awkward refs.
 
 ```tsx
 function ForwardMessageComposer() {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
 
   return (
     <Composer.Frame>
       <Composer.Input />
       <Composer.Footer />
     </Composer.Frame>
-  )
+  );
 }
 
 // Problem: How does this button access composer state?
@@ -37,7 +37,7 @@ function ForwardMessageDialog() {
         <ForwardButton /> {/* Needs to call submit */}
       </DialogActions>
     </Dialog>
-  )
+  );
 }
 ```
 
@@ -45,20 +45,20 @@ function ForwardMessageDialog() {
 
 ```tsx
 function ForwardMessageDialog() {
-  const [input, setInput] = useState('')
+  const [input, setInput] = useState('');
   return (
     <Dialog>
       <ForwardMessageComposer onInputChange={setInput} />
       <MessagePreview input={input} />
     </Dialog>
-  )
+  );
 }
 
 function ForwardMessageComposer({ onInputChange }) {
-  const [state, setState] = useState(initialState)
+  const [state, setState] = useState(initialState);
   useEffect(() => {
-    onInputChange(state.input) // Sync on every change 😬
-  }, [state.input])
+    onInputChange(state.input); // Sync on every change 😬
+  }, [state.input]);
 }
 ```
 
@@ -66,13 +66,13 @@ function ForwardMessageComposer({ onInputChange }) {
 
 ```tsx
 function ForwardMessageDialog() {
-  const stateRef = useRef(null)
+  const stateRef = useRef(null);
   return (
     <Dialog>
       <ForwardMessageComposer stateRef={stateRef} />
       <ForwardButton onPress={() => submit(stateRef.current)} />
     </Dialog>
-  )
+  );
 }
 ```
 
@@ -80,9 +80,9 @@ function ForwardMessageDialog() {
 
 ```tsx
 function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
-  const [state, setState] = useState(initialState)
-  const forwardMessage = useForwardMessage()
-  const inputRef = useRef(null)
+  const [state, setState] = useState(initialState);
+  const forwardMessage = useForwardMessage();
+  const inputRef = useRef(null);
 
   return (
     <Composer.Provider
@@ -92,7 +92,7 @@ function ForwardMessageProvider({ children }: { children: React.ReactNode }) {
     >
       {children}
     </Composer.Provider>
-  )
+  );
 }
 
 function ForwardMessageDialog() {
@@ -107,12 +107,12 @@ function ForwardMessageDialog() {
         </DialogActions>
       </Dialog>
     </ForwardMessageProvider>
-  )
+  );
 }
 
 function ForwardButton() {
-  const { actions } = use(Composer.Context)
-  return <Button onPress={actions.submit}>Forward</Button>
+  const { actions } = use(Composer.Context);
+  return <Button onPress={actions.submit}>Forward</Button>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/SKILL.md

@@ -4,7 +4,7 @@ description: React and Next.js performance optimization guidelines from Vercel E
 license: MIT
 metadata:
   author: vercel
-  version: "1.0.0"
+  version: '1.0.0'
 ---
 
 # Vercel React Best Practices
@@ -14,6 +14,7 @@ Comprehensive performance optimization guide for React and Next.js applications,
 ## When to Apply
 
 Reference these guidelines when:
+
 - Writing new React components or Next.js pages
 - Implementing data fetching (client or server-side)
 - Reviewing code for performance issues
@@ -22,16 +23,16 @@ Reference these guidelines when:
 
 ## Rule Categories by Priority
 
-| Priority | Category | Impact | Prefix |
-|----------|----------|--------|--------|
-| 1 | Eliminating Waterfalls | CRITICAL | `async-` |
-| 2 | Bundle Size Optimization | CRITICAL | `bundle-` |
-| 3 | Server-Side Performance | HIGH | `server-` |
-| 4 | Client-Side Data Fetching | MEDIUM-HIGH | `client-` |
-| 5 | Re-render Optimization | MEDIUM | `rerender-` |
-| 6 | Rendering Performance | MEDIUM | `rendering-` |
-| 7 | JavaScript Performance | LOW-MEDIUM | `js-` |
-| 8 | Advanced Patterns | LOW | `advanced-` |
+| Priority | Category                  | Impact      | Prefix       |
+| -------- | ------------------------- | ----------- | ------------ |
+| 1        | Eliminating Waterfalls    | CRITICAL    | `async-`     |
+| 2        | Bundle Size Optimization  | CRITICAL    | `bundle-`    |
+| 3        | Server-Side Performance   | HIGH        | `server-`    |
+| 4        | Client-Side Data Fetching | MEDIUM-HIGH | `client-`    |
+| 5        | Re-render Optimization    | MEDIUM      | `rerender-`  |
+| 6        | Rendering Performance     | MEDIUM      | `rendering-` |
+| 7        | JavaScript Performance    | LOW-MEDIUM  | `js-`        |
+| 8        | Advanced Patterns         | LOW         | `advanced-`  |
 
 ## Quick Reference
 
@@ -126,6 +127,7 @@ rules/bundle-barrel-imports.md
 ```
 
 Each rule file contains:
+
 - Brief explanation of why it matters
 - Incorrect code example with explanation
 - Correct code example with explanation

.agent/skills/vercel-react-best-practices/rules/advanced-event-handler-refs.md

@@ -14,9 +14,9 @@ Store callbacks in refs when used in effects that shouldn't re-subscribe on call
 ```tsx
 function useWindowEvent(event: string, handler: (e) => void) {
   useEffect(() => {
-    window.addEventListener(event, handler)
-    return () => window.removeEventListener(event, handler)
-  }, [event, handler])
+    window.addEventListener(event, handler);
+    return () => window.removeEventListener(event, handler);
+  }, [event, handler]);
 }
 ```
 
@@ -24,31 +24,31 @@ function useWindowEvent(event: string, handler: (e) => void) {
 
 ```tsx
 function useWindowEvent(event: string, handler: (e) => void) {
-  const handlerRef = useRef(handler)
+  const handlerRef = useRef(handler);
   useEffect(() => {
-    handlerRef.current = handler
-  }, [handler])
+    handlerRef.current = handler;
+  }, [handler]);
 
   useEffect(() => {
-    const listener = (e) => handlerRef.current(e)
-    window.addEventListener(event, listener)
-    return () => window.removeEventListener(event, listener)
-  }, [event])
+    const listener = (e) => handlerRef.current(e);
+    window.addEventListener(event, listener);
+    return () => window.removeEventListener(event, listener);
+  }, [event]);
 }
 ```
 
 **Alternative: use `useEffectEvent` if you're on latest React:**
 
 ```tsx
-import { useEffectEvent } from 'react'
+import { useEffectEvent } from 'react';
 
 function useWindowEvent(event: string, handler: (e) => void) {
-  const onEvent = useEffectEvent(handler)
+  const onEvent = useEffectEvent(handler);
 
   useEffect(() => {
-    window.addEventListener(event, onEvent)
-    return () => window.removeEventListener(event, onEvent)
-  }, [event])
+    window.addEventListener(event, onEvent);
+    return () => window.removeEventListener(event, onEvent);
+  }, [event]);
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/advanced-init-once.md

@@ -14,9 +14,9 @@ Do not put app-wide initialization that must run once per app load inside `useEf
 ```tsx
 function Comp() {
   useEffect(() => {
-    loadFromStorage()
-    checkAuthToken()
-  }, [])
+    loadFromStorage();
+    checkAuthToken();
+  }, []);
 
   // ...
 }
@@ -25,15 +25,15 @@ function Comp() {
 **Correct (once per app load):**
 
 ```tsx
-let didInit = false
+let didInit = false;
 
 function Comp() {
   useEffect(() => {
-    if (didInit) return
-    didInit = true
-    loadFromStorage()
-    checkAuthToken()
-  }, [])
+    if (didInit) return;
+    didInit = true;
+    loadFromStorage();
+    checkAuthToken();
+  }, []);
 
   // ...
 }

.agent/skills/vercel-react-best-practices/rules/advanced-use-latest.md

@@ -13,12 +13,12 @@ Access latest values in callbacks without adding them to dependency arrays. Prev
 
 ```tsx
 function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
-  const [query, setQuery] = useState('')
+  const [query, setQuery] = useState('');
 
   useEffect(() => {
-    const timeout = setTimeout(() => onSearch(query), 300)
-    return () => clearTimeout(timeout)
-  }, [query, onSearch])
+    const timeout = setTimeout(() => onSearch(query), 300);
+    return () => clearTimeout(timeout);
+  }, [query, onSearch]);
 }
 ```
 
@@ -28,12 +28,12 @@ function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
 import { useEffectEvent } from 'react';
 
 function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
-  const [query, setQuery] = useState('')
-  const onSearchEvent = useEffectEvent(onSearch)
+  const [query, setQuery] = useState('');
+  const onSearchEvent = useEffectEvent(onSearch);
 
   useEffect(() => {
-    const timeout = setTimeout(() => onSearchEvent(query), 300)
-    return () => clearTimeout(timeout)
-  }, [query])
+    const timeout = setTimeout(() => onSearchEvent(query), 300);
+    return () => clearTimeout(timeout);
+  }, [query]);
 }
 ```

.agent/skills/vercel-react-best-practices/rules/async-api-routes.md

@@ -13,10 +13,10 @@ In API routes and Server Actions, start independent operations immediately, even
 
 ```typescript
 export async function GET(request: Request) {
-  const session = await auth()
-  const config = await fetchConfig()
-  const data = await fetchData(session.user.id)
-  return Response.json({ data, config })
+  const session = await auth();
+  const config = await fetchConfig();
+  const data = await fetchData(session.user.id);
+  return Response.json({ data, config });
 }
 ```
 
@@ -24,14 +24,11 @@ export async function GET(request: Request) {
 
 ```typescript
 export async function GET(request: Request) {
-  const sessionPromise = auth()
-  const configPromise = fetchConfig()
-  const session = await sessionPromise
-  const [config, data] = await Promise.all([
-    configPromise,
-    fetchData(session.user.id)
-  ])
-  return Response.json({ data, config })
+  const sessionPromise = auth();
+  const configPromise = fetchConfig();
+  const session = await sessionPromise;
+  const [config, data] = await Promise.all([configPromise, fetchData(session.user.id)]);
+  return Response.json({ data, config });
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/async-defer-await.md

@@ -13,15 +13,15 @@ Move `await` operations into the branches where they're actually used to avoid b
 
 ```typescript
 async function handleRequest(userId: string, skipProcessing: boolean) {
-  const userData = await fetchUserData(userId)
-  
+  const userData = await fetchUserData(userId);
+
   if (skipProcessing) {
     // Returns immediately but still waited for userData
-    return { skipped: true }
+    return { skipped: true };
   }
-  
+
   // Only this branch uses userData
-  return processUserData(userData)
+  return processUserData(userData);
 }
 ```
 
@@ -31,12 +31,12 @@ async function handleRequest(userId: string, skipProcessing: boolean) {
 async function handleRequest(userId: string, skipProcessing: boolean) {
   if (skipProcessing) {
     // Returns immediately without waiting
-    return { skipped: true }
+    return { skipped: true };
   }
-  
+
   // Fetch only when needed
-  const userData = await fetchUserData(userId)
-  return processUserData(userData)
+  const userData = await fetchUserData(userId);
+  return processUserData(userData);
 }
 ```
 
@@ -45,35 +45,35 @@ async function handleRequest(userId: string, skipProcessing: boolean) {
 ```typescript
 // Incorrect: always fetches permissions
 async function updateResource(resourceId: string, userId: string) {
-  const permissions = await fetchPermissions(userId)
-  const resource = await getResource(resourceId)
-  
+  const permissions = await fetchPermissions(userId);
+  const resource = await getResource(resourceId);
+
   if (!resource) {
-    return { error: 'Not found' }
+    return { error: 'Not found' };
   }
-  
+
   if (!permissions.canEdit) {
-    return { error: 'Forbidden' }
+    return { error: 'Forbidden' };
   }
-  
-  return await updateResourceData(resource, permissions)
+
+  return await updateResourceData(resource, permissions);
 }
 
 // Correct: fetches only when needed
 async function updateResource(resourceId: string, userId: string) {
-  const resource = await getResource(resourceId)
-  
+  const resource = await getResource(resourceId);
+
   if (!resource) {
-    return { error: 'Not found' }
+    return { error: 'Not found' };
   }
-  
-  const permissions = await fetchPermissions(userId)
-  
+
+  const permissions = await fetchPermissions(userId);
+
   if (!permissions.canEdit) {
-    return { error: 'Forbidden' }
+    return { error: 'Forbidden' };
   }
-  
-  return await updateResourceData(resource, permissions)
+
+  return await updateResourceData(resource, permissions);
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/async-dependencies.md

@@ -12,25 +12,26 @@ For operations with partial dependencies, use `better-all` to maximize paralleli
 **Incorrect (profile waits for config unnecessarily):**
 
 ```typescript
-const [user, config] = await Promise.all([
-  fetchUser(),
-  fetchConfig()
-])
-const profile = await fetchProfile(user.id)
+const [user, config] = await Promise.all([fetchUser(), fetchConfig()]);
+const profile = await fetchProfile(user.id);
 ```
 
 **Correct (config and profile run in parallel):**
 
 ```typescript
-import { all } from 'better-all'
+import { all } from 'better-all';
 
 const { user, config, profile } = await all({
-  async user() { return fetchUser() },
-  async config() { return fetchConfig() },
+  async user() {
+    return fetchUser();
+  },
+  async config() {
+    return fetchConfig();
+  },
   async profile() {
-    return fetchProfile((await this.$.user).id)
-  }
-})
+    return fetchProfile((await this.$.user).id);
+  },
+});
 ```
 
 **Alternative without extra dependencies:**
@@ -38,14 +39,10 @@ const { user, config, profile } = await all({
 We can also create all the promises first, and do `Promise.all()` at the end.
 
 ```typescript
-const userPromise = fetchUser()
-const profilePromise = userPromise.then(user => fetchProfile(user.id))
+const userPromise = fetchUser();
+const profilePromise = userPromise.then((user) => fetchProfile(user.id));
 
-const [user, config, profile] = await Promise.all([
-  userPromise,
-  fetchConfig(),
-  profilePromise
-])
+const [user, config, profile] = await Promise.all([userPromise, fetchConfig(), profilePromise]);
 ```
 
 Reference: [https://github.com/shuding/better-all](https://github.com/shuding/better-all)

.agent/skills/vercel-react-best-practices/rules/async-parallel.md

@@ -12,17 +12,13 @@ When async operations have no interdependencies, execute them concurrently using
 **Incorrect (sequential execution, 3 round trips):**
 
 ```typescript
-const user = await fetchUser()
-const posts = await fetchPosts()
-const comments = await fetchComments()
+const user = await fetchUser();
+const posts = await fetchPosts();
+const comments = await fetchComments();
 ```
 
 **Correct (parallel execution, 1 round trip):**
 
 ```typescript
-const [user, posts, comments] = await Promise.all([
-  fetchUser(),
-  fetchPosts(),
-  fetchComments()
-])
+const [user, posts, comments] = await Promise.all([fetchUser(), fetchPosts(), fetchComments()]);
 ```

.agent/skills/vercel-react-best-practices/rules/async-suspense-boundaries.md

@@ -13,8 +13,8 @@ Instead of awaiting data in async components before returning JSX, use Suspense
 
 ```tsx
 async function Page() {
-  const data = await fetchData() // Blocks entire page
-  
+  const data = await fetchData(); // Blocks entire page
+
   return (
     <div>
       <div>Sidebar</div>
@@ -24,7 +24,7 @@ async function Page() {
       </div>
       <div>Footer</div>
     </div>
-  )
+  );
 }
 ```
 
@@ -45,12 +45,12 @@ function Page() {
       </div>
       <div>Footer</div>
     </div>
-  )
+  );
 }
 
 async function DataDisplay() {
-  const data = await fetchData() // Only blocks this component
-  return <div>{data.content}</div>
+  const data = await fetchData(); // Only blocks this component
+  return <div>{data.content}</div>;
 }
 ```
 
@@ -61,8 +61,8 @@ Sidebar, Header, and Footer render immediately. Only DataDisplay waits for data.
 ```tsx
 function Page() {
   // Start fetch immediately, but don't await
-  const dataPromise = fetchData()
-  
+  const dataPromise = fetchData();
+
   return (
     <div>
       <div>Sidebar</div>
@@ -73,17 +73,17 @@ function Page() {
       </Suspense>
       <div>Footer</div>
     </div>
-  )
+  );
 }
 
 function DataDisplay({ dataPromise }: { dataPromise: Promise<Data> }) {
-  const data = use(dataPromise) // Unwraps the promise
-  return <div>{data.content}</div>
+  const data = use(dataPromise); // Unwraps the promise
+  return <div>{data.content}</div>;
 }
 
 function DataSummary({ dataPromise }: { dataPromise: Promise<Data> }) {
-  const data = use(dataPromise) // Reuses the same promise
-  return <div>{data.summary}</div>
+  const data = use(dataPromise); // Reuses the same promise
+  return <div>{data.summary}</div>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/bundle-barrel-imports.md

@@ -16,24 +16,24 @@ Popular icon and component libraries can have **up to 10,000 re-exports** in the
 **Incorrect (imports entire library):**
 
 ```tsx
-import { Check, X, Menu } from 'lucide-react'
+import { Check, X, Menu } from 'lucide-react';
 // Loads 1,583 modules, takes ~2.8s extra in dev
 // Runtime cost: 200-800ms on every cold start
 
-import { Button, TextField } from '@mui/material'
+import { Button, TextField } from '@mui/material';
 // Loads 2,225 modules, takes ~4.2s extra in dev
 ```
 
 **Correct (imports only what you need):**
 
 ```tsx
-import Check from 'lucide-react/dist/esm/icons/check'
-import X from 'lucide-react/dist/esm/icons/x'
-import Menu from 'lucide-react/dist/esm/icons/menu'
+import Check from 'lucide-react/dist/esm/icons/check';
+import X from 'lucide-react/dist/esm/icons/x';
+import Menu from 'lucide-react/dist/esm/icons/menu';
 // Loads only 3 modules (~2KB vs ~1MB)
 
-import Button from '@mui/material/Button'
-import TextField from '@mui/material/TextField'
+import Button from '@mui/material/Button';
+import TextField from '@mui/material/TextField';
 // Loads only what you use
 ```
 
@@ -43,12 +43,12 @@ import TextField from '@mui/material/TextField'
 // next.config.js - use optimizePackageImports
 module.exports = {
   experimental: {
-    optimizePackageImports: ['lucide-react', '@mui/material']
-  }
-}
+    optimizePackageImports: ['lucide-react', '@mui/material'],
+  },
+};
 
 // Then you can keep the ergonomic barrel imports:
-import { Check, X, Menu } from 'lucide-react'
+import { Check, X, Menu } from 'lucide-react';
 // Automatically transformed to direct imports at build time
 ```
 

.agent/skills/vercel-react-best-practices/rules/bundle-conditional.md

@@ -12,19 +12,25 @@ Load large data or modules only when a feature is activated.
 **Example (lazy-load animation frames):**
 
 ```tsx
-function AnimationPlayer({ enabled, setEnabled }: { enabled: boolean; setEnabled: React.Dispatch<React.SetStateAction<boolean>> }) {
-  const [frames, setFrames] = useState<Frame[] | null>(null)
+function AnimationPlayer({
+  enabled,
+  setEnabled,
+}: {
+  enabled: boolean;
+  setEnabled: React.Dispatch<React.SetStateAction<boolean>>;
+}) {
+  const [frames, setFrames] = useState<Frame[] | null>(null);
 
   useEffect(() => {
     if (enabled && !frames && typeof window !== 'undefined') {
       import('./animation-frames.js')
-        .then(mod => setFrames(mod.frames))
-        .catch(() => setEnabled(false))
+        .then((mod) => setFrames(mod.frames))
+        .catch(() => setEnabled(false));
     }
-  }, [enabled, frames, setEnabled])
+  }, [enabled, frames, setEnabled]);
 
-  if (!frames) return <Skeleton />
-  return <Canvas frames={frames} />
+  if (!frames) return <Skeleton />;
+  return <Canvas frames={frames} />;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/bundle-defer-third-party.md

@@ -12,7 +12,7 @@ Analytics, logging, and error tracking don't block user interaction. Load them a
 **Incorrect (blocks initial bundle):**
 
 ```tsx
-import { Analytics } from '@vercel/analytics/react'
+import { Analytics } from '@vercel/analytics/react';
 
 export default function RootLayout({ children }) {
   return (
@@ -22,19 +22,18 @@ export default function RootLayout({ children }) {
         <Analytics />
       </body>
     </html>
-  )
+  );
 }
 ```
 
 **Correct (loads after hydration):**
 
 ```tsx
-import dynamic from 'next/dynamic'
+import dynamic from 'next/dynamic';
 
-const Analytics = dynamic(
-  () => import('@vercel/analytics/react').then(m => m.Analytics),
-  { ssr: false }
-)
+const Analytics = dynamic(() => import('@vercel/analytics/react').then((m) => m.Analytics), {
+  ssr: false,
+});
 
 export default function RootLayout({ children }) {
   return (
@@ -44,6 +43,6 @@ export default function RootLayout({ children }) {
         <Analytics />
       </body>
     </html>
-  )
+  );
 }
 ```

.agent/skills/vercel-react-best-practices/rules/bundle-dynamic-imports.md

@@ -12,24 +12,23 @@ Use `next/dynamic` to lazy-load large components not needed on initial render.
 **Incorrect (Monaco bundles with main chunk ~300KB):**
 
 ```tsx
-import { MonacoEditor } from './monaco-editor'
+import { MonacoEditor } from './monaco-editor';
 
 function CodePanel({ code }: { code: string }) {
-  return <MonacoEditor value={code} />
+  return <MonacoEditor value={code} />;
 }
 ```
 
 **Correct (Monaco loads on demand):**
 
 ```tsx
-import dynamic from 'next/dynamic'
+import dynamic from 'next/dynamic';
 
-const MonacoEditor = dynamic(
-  () => import('./monaco-editor').then(m => m.MonacoEditor),
-  { ssr: false }
-)
+const MonacoEditor = dynamic(() => import('./monaco-editor').then((m) => m.MonacoEditor), {
+  ssr: false,
+});
 
 function CodePanel({ code }: { code: string }) {
-  return <MonacoEditor value={code} />
+  return <MonacoEditor value={code} />;
 }
 ```

.agent/skills/vercel-react-best-practices/rules/bundle-preload.md

@@ -15,19 +15,15 @@ Preload heavy bundles before they're needed to reduce perceived latency.
 function EditorButton({ onClick }: { onClick: () => void }) {
   const preload = () => {
     if (typeof window !== 'undefined') {
-      void import('./monaco-editor')
+      void import('./monaco-editor');
     }
-  }
+  };
 
   return (
-    <button
-      onMouseEnter={preload}
-      onFocus={preload}
-      onClick={onClick}
-    >
+    <button onMouseEnter={preload} onFocus={preload} onClick={onClick}>
       Open Editor
     </button>
-  )
+  );
 }
 ```
 
@@ -37,13 +33,11 @@ function EditorButton({ onClick }: { onClick: () => void }) {
 function FlagsProvider({ children, flags }: Props) {
   useEffect(() => {
     if (flags.editorEnabled && typeof window !== 'undefined') {
-      void import('./monaco-editor').then(mod => mod.init())
+      void import('./monaco-editor').then((mod) => mod.init());
     }
-  }, [flags.editorEnabled])
+  }, [flags.editorEnabled]);
 
-  return <FlagsContext.Provider value={flags}>
-    {children}
-  </FlagsContext.Provider>
+  return <FlagsContext.Provider value={flags}>{children}</FlagsContext.Provider>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/client-event-listeners.md

@@ -16,12 +16,12 @@ function useKeyboardShortcut(key: string, callback: () => void) {
   useEffect(() => {
     const handler = (e: KeyboardEvent) => {
       if (e.metaKey && e.key === key) {
-        callback()
+        callback();
       }
-    }
-    window.addEventListener('keydown', handler)
-    return () => window.removeEventListener('keydown', handler)
-  }, [key, callback])
+    };
+    window.addEventListener('keydown', handler);
+    return () => window.removeEventListener('keydown', handler);
+  }, [key, callback]);
 }
 ```
 
@@ -30,45 +30,49 @@ When using the `useKeyboardShortcut` hook multiple times, each instance will reg
 **Correct (N instances = 1 listener):**
 
 ```tsx
-import useSWRSubscription from 'swr/subscription'
+import useSWRSubscription from 'swr/subscription';
 
 // Module-level Map to track callbacks per key
-const keyCallbacks = new Map<string, Set<() => void>>()
+const keyCallbacks = new Map<string, Set<() => void>>();
 
 function useKeyboardShortcut(key: string, callback: () => void) {
   // Register this callback in the Map
   useEffect(() => {
     if (!keyCallbacks.has(key)) {
-      keyCallbacks.set(key, new Set())
+      keyCallbacks.set(key, new Set());
     }
-    keyCallbacks.get(key)!.add(callback)
+    keyCallbacks.get(key)!.add(callback);
 
     return () => {
-      const set = keyCallbacks.get(key)
+      const set = keyCallbacks.get(key);
       if (set) {
-        set.delete(callback)
+        set.delete(callback);
         if (set.size === 0) {
-          keyCallbacks.delete(key)
+          keyCallbacks.delete(key);
         }
       }
-    }
-  }, [key, callback])
+    };
+  }, [key, callback]);
 
   useSWRSubscription('global-keydown', () => {
     const handler = (e: KeyboardEvent) => {
       if (e.metaKey && keyCallbacks.has(e.key)) {
-        keyCallbacks.get(e.key)!.forEach(cb => cb())
+        keyCallbacks.get(e.key)!.forEach((cb) => cb());
       }
-    }
-    window.addEventListener('keydown', handler)
-    return () => window.removeEventListener('keydown', handler)
-  })
+    };
+    window.addEventListener('keydown', handler);
+    return () => window.removeEventListener('keydown', handler);
+  });
 }
 
 function Profile() {
   // Multiple shortcuts will share the same listener
-  useKeyboardShortcut('p', () => { /* ... */ }) 
-  useKeyboardShortcut('k', () => { /* ... */ })
+  useKeyboardShortcut('p', () => {
+    /* ... */
+  });
+  useKeyboardShortcut('k', () => {
+    /* ... */
+  });
   // ...
 }
 ```

.agent/skills/vercel-react-best-practices/rules/client-localstorage-schema.md

@@ -13,18 +13,18 @@ Add version prefix to keys and store only needed fields. Prevents schema conflic
 
 ```typescript
 // No version, stores everything, no error handling
-localStorage.setItem('userConfig', JSON.stringify(fullUserObject))
-const data = localStorage.getItem('userConfig')
+localStorage.setItem('userConfig', JSON.stringify(fullUserObject));
+const data = localStorage.getItem('userConfig');
 ```
 
 **Correct:**
 
 ```typescript
-const VERSION = 'v2'
+const VERSION = 'v2';
 
 function saveConfig(config: { theme: string; language: string }) {
   try {
-    localStorage.setItem(`userConfig:${VERSION}`, JSON.stringify(config))
+    localStorage.setItem(`userConfig:${VERSION}`, JSON.stringify(config));
   } catch {
     // Throws in incognito/private browsing, quota exceeded, or disabled
   }
@@ -32,21 +32,21 @@ function saveConfig(config: { theme: string; language: string }) {
 
 function loadConfig() {
   try {
-    const data = localStorage.getItem(`userConfig:${VERSION}`)
-    return data ? JSON.parse(data) : null
+    const data = localStorage.getItem(`userConfig:${VERSION}`);
+    return data ? JSON.parse(data) : null;
   } catch {
-    return null
+    return null;
   }
 }
 
 // Migration from v1 to v2
 function migrate() {
   try {
-    const v1 = localStorage.getItem('userConfig:v1')
+    const v1 = localStorage.getItem('userConfig:v1');
     if (v1) {
-      const old = JSON.parse(v1)
-      saveConfig({ theme: old.darkMode ? 'dark' : 'light', language: old.lang })
-      localStorage.removeItem('userConfig:v1')
+      const old = JSON.parse(v1);
+      saveConfig({ theme: old.darkMode ? 'dark' : 'light', language: old.lang });
+      localStorage.removeItem('userConfig:v1');
     }
   } catch {}
 }
@@ -58,10 +58,13 @@ function migrate() {
 // User object has 20+ fields, only store what UI needs
 function cachePrefs(user: FullUser) {
   try {
-    localStorage.setItem('prefs:v1', JSON.stringify({
-      theme: user.preferences.theme,
-      notifications: user.preferences.notifications
-    }))
+    localStorage.setItem(
+      'prefs:v1',
+      JSON.stringify({
+        theme: user.preferences.theme,
+        notifications: user.preferences.notifications,
+      }),
+    );
   } catch {}
 }
 ```

.agent/skills/vercel-react-best-practices/rules/client-passive-event-listeners.md

@@ -13,34 +13,34 @@ Add `{ passive: true }` to touch and wheel event listeners to enable immediate s
 
 ```typescript
 useEffect(() => {
-  const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX)
-  const handleWheel = (e: WheelEvent) => console.log(e.deltaY)
-  
-  document.addEventListener('touchstart', handleTouch)
-  document.addEventListener('wheel', handleWheel)
-  
+  const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX);
+  const handleWheel = (e: WheelEvent) => console.log(e.deltaY);
+
+  document.addEventListener('touchstart', handleTouch);
+  document.addEventListener('wheel', handleWheel);
+
   return () => {
-    document.removeEventListener('touchstart', handleTouch)
-    document.removeEventListener('wheel', handleWheel)
-  }
-}, [])
+    document.removeEventListener('touchstart', handleTouch);
+    document.removeEventListener('wheel', handleWheel);
+  };
+}, []);
 ```
 
 **Correct:**
 
 ```typescript
 useEffect(() => {
-  const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX)
-  const handleWheel = (e: WheelEvent) => console.log(e.deltaY)
-  
-  document.addEventListener('touchstart', handleTouch, { passive: true })
-  document.addEventListener('wheel', handleWheel, { passive: true })
-  
+  const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX);
+  const handleWheel = (e: WheelEvent) => console.log(e.deltaY);
+
+  document.addEventListener('touchstart', handleTouch, { passive: true });
+  document.addEventListener('wheel', handleWheel, { passive: true });
+
   return () => {
-    document.removeEventListener('touchstart', handleTouch)
-    document.removeEventListener('wheel', handleWheel)
-  }
-}, [])
+    document.removeEventListener('touchstart', handleTouch);
+    document.removeEventListener('wheel', handleWheel);
+  };
+}, []);
 ```
 
 **Use passive when:** tracking/analytics, logging, any listener that doesn't call `preventDefault()`.

.agent/skills/vercel-react-best-practices/rules/client-swr-dedup.md

@@ -13,43 +13,43 @@ SWR enables request deduplication, caching, and revalidation across component in
 
 ```tsx
 function UserList() {
-  const [users, setUsers] = useState([])
+  const [users, setUsers] = useState([]);
   useEffect(() => {
     fetch('/api/users')
-      .then(r => r.json())
-      .then(setUsers)
-  }, [])
+      .then((r) => r.json())
+      .then(setUsers);
+  }, []);
 }
 ```
 
 **Correct (multiple instances share one request):**
 
 ```tsx
-import useSWR from 'swr'
+import useSWR from 'swr';
 
 function UserList() {
-  const { data: users } = useSWR('/api/users', fetcher)
+  const { data: users } = useSWR('/api/users', fetcher);
 }
 ```
 
 **For immutable data:**
 
 ```tsx
-import { useImmutableSWR } from '@/lib/swr'
+import { useImmutableSWR } from '@/lib/swr';
 
 function StaticContent() {
-  const { data } = useImmutableSWR('/api/config', fetcher)
+  const { data } = useImmutableSWR('/api/config', fetcher);
 }
 ```
 
 **For mutations:**
 
 ```tsx
-import { useSWRMutation } from 'swr/mutation'
+import { useSWRMutation } from 'swr/mutation';
 
 function UpdateButton() {
-  const { trigger } = useSWRMutation('/api/user', updateUser)
-  return <button onClick={() => trigger()}>Update</button>
+  const { trigger } = useSWRMutation('/api/user', updateUser);
+  return <button onClick={() => trigger()}>Update</button>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/js-batch-dom-css.md

@@ -10,55 +10,60 @@ tags: javascript, dom, css, performance, reflow, layout-thrashing
 Avoid interleaving style writes with layout reads. When you read a layout property (like `offsetWidth`, `getBoundingClientRect()`, or `getComputedStyle()`) between style changes, the browser is forced to trigger a synchronous reflow.
 
 **This is OK (browser batches style changes):**
+
 ```typescript
 function updateElementStyles(element: HTMLElement) {
   // Each line invalidates style, but browser batches the recalculation
-  element.style.width = '100px'
-  element.style.height = '200px'
-  element.style.backgroundColor = 'blue'
-  element.style.border = '1px solid black'
+  element.style.width = '100px';
+  element.style.height = '200px';
+  element.style.backgroundColor = 'blue';
+  element.style.border = '1px solid black';
 }
 ```
 
 **Incorrect (interleaved reads and writes force reflows):**
+
 ```typescript
 function layoutThrashing(element: HTMLElement) {
-  element.style.width = '100px'
-  const width = element.offsetWidth  // Forces reflow
-  element.style.height = '200px'
-  const height = element.offsetHeight  // Forces another reflow
+  element.style.width = '100px';
+  const width = element.offsetWidth; // Forces reflow
+  element.style.height = '200px';
+  const height = element.offsetHeight; // Forces another reflow
 }
 ```
 
 **Correct (batch writes, then read once):**
+
 ```typescript
 function updateElementStyles(element: HTMLElement) {
   // Batch all writes together
-  element.style.width = '100px'
-  element.style.height = '200px'
-  element.style.backgroundColor = 'blue'
-  element.style.border = '1px solid black'
-  
+  element.style.width = '100px';
+  element.style.height = '200px';
+  element.style.backgroundColor = 'blue';
+  element.style.border = '1px solid black';
+
   // Read after all writes are done (single reflow)
-  const { width, height } = element.getBoundingClientRect()
+  const { width, height } = element.getBoundingClientRect();
 }
 ```
 
 **Correct (batch reads, then writes):**
+
 ```typescript
 function avoidThrashing(element: HTMLElement) {
   // Read phase - all layout queries first
-  const rect1 = element.getBoundingClientRect()
-  const offsetWidth = element.offsetWidth
-  const offsetHeight = element.offsetHeight
-  
+  const rect1 = element.getBoundingClientRect();
+  const offsetWidth = element.offsetWidth;
+  const offsetHeight = element.offsetHeight;
+
   // Write phase - all style changes after
-  element.style.width = '100px'
-  element.style.height = '200px'
+  element.style.width = '100px';
+  element.style.height = '200px';
 }
 ```
 
 **Better: use CSS classes**
+
 ```css
 .highlighted-box {
   width: 100px;
@@ -67,38 +72,36 @@ function avoidThrashing(element: HTMLElement) {
   border: 1px solid black;
 }
 ```
+
 ```typescript
 function updateElementStyles(element: HTMLElement) {
-  element.classList.add('highlighted-box')
-  
-  const { width, height } = element.getBoundingClientRect()
+  element.classList.add('highlighted-box');
+
+  const { width, height } = element.getBoundingClientRect();
 }
 ```
 
 **React example:**
+
 ```tsx
 // Incorrect: interleaving style changes with layout queries
 function Box({ isHighlighted }: { isHighlighted: boolean }) {
-  const ref = useRef<HTMLDivElement>(null)
-  
+  const ref = useRef<HTMLDivElement>(null);
+
   useEffect(() => {
     if (ref.current && isHighlighted) {
-      ref.current.style.width = '100px'
-      const width = ref.current.offsetWidth // Forces layout
-      ref.current.style.height = '200px'
+      ref.current.style.width = '100px';
+      const width = ref.current.offsetWidth; // Forces layout
+      ref.current.style.height = '200px';
     }
-  }, [isHighlighted])
-  
-  return <div ref={ref}>Content</div>
+  }, [isHighlighted]);
+
+  return <div ref={ref}>Content</div>;
 }
 
 // Correct: toggle class
 function Box({ isHighlighted }: { isHighlighted: boolean }) {
-  return (
-    <div className={isHighlighted ? 'highlighted-box' : ''}>
-      Content
-    </div>
-  )
+  return <div className={isHighlighted ? 'highlighted-box' : ''}>Content</div>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/js-cache-function-results.md

@@ -18,7 +18,7 @@ function ProjectList({ projects }: { projects: Project[] }) {
       {projects.map(project => {
         // slugify() called 100+ times for same project names
         const slug = slugify(project.name)
-        
+
         return <ProjectCard key={project.id} slug={slug} />
       })}
     </div>
@@ -47,7 +47,7 @@ function ProjectList({ projects }: { projects: Project[] }) {
       {projects.map(project => {
         // Computed only once per unique project name
         const slug = cachedSlugify(project.name)
-        
+
         return <ProjectCard key={project.id} slug={slug} />
       })}
     </div>
@@ -58,20 +58,20 @@ function ProjectList({ projects }: { projects: Project[] }) {
 **Simpler pattern for single-value functions:**
 
 ```typescript
-let isLoggedInCache: boolean | null = null
+let isLoggedInCache: boolean | null = null;
 
 function isLoggedIn(): boolean {
   if (isLoggedInCache !== null) {
-    return isLoggedInCache
+    return isLoggedInCache;
   }
-  
-  isLoggedInCache = document.cookie.includes('auth=')
-  return isLoggedInCache
+
+  isLoggedInCache = document.cookie.includes('auth=');
+  return isLoggedInCache;
 }
 
 // Clear cache when auth changes
 function onAuthChange() {
-  isLoggedInCache = null
+  isLoggedInCache = null;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/js-cache-property-access.md

@@ -13,16 +13,16 @@ Cache object property lookups in hot paths.
 
 ```typescript
 for (let i = 0; i < arr.length; i++) {
-  process(obj.config.settings.value)
+  process(obj.config.settings.value);
 }
 ```
 
 **Correct (1 lookup total):**
 
 ```typescript
-const value = obj.config.settings.value
-const len = arr.length
+const value = obj.config.settings.value;
+const len = arr.length;
 for (let i = 0; i < len; i++) {
-  process(value)
+  process(value);
 }
 ```

.agent/skills/vercel-react-best-practices/rules/js-cache-storage.md

@@ -13,7 +13,7 @@ tags: javascript, localStorage, storage, caching, performance
 
 ```typescript
 function getTheme() {
-  return localStorage.getItem('theme') ?? 'light'
+  return localStorage.getItem('theme') ?? 'light';
 }
 // Called 10 times = 10 storage reads
 ```
@@ -21,18 +21,18 @@ function getTheme() {
 **Correct (Map cache):**
 
 ```typescript
-const storageCache = new Map<string, string | null>()
+const storageCache = new Map<string, string | null>();
 
 function getLocalStorage(key: string) {
   if (!storageCache.has(key)) {
-    storageCache.set(key, localStorage.getItem(key))
+    storageCache.set(key, localStorage.getItem(key));
   }
-  return storageCache.get(key)
+  return storageCache.get(key);
 }
 
 function setLocalStorage(key: string, value: string) {
-  localStorage.setItem(key, value)
-  storageCache.set(key, value)  // keep cache in sync
+  localStorage.setItem(key, value);
+  storageCache.set(key, value); // keep cache in sync
 }
 ```
 
@@ -41,15 +41,13 @@ Use a Map (not a hook) so it works everywhere: utilities, event handlers, not ju
 **Cookie caching:**
 
 ```typescript
-let cookieCache: Record<string, string> | null = null
+let cookieCache: Record<string, string> | null = null;
 
 function getCookie(name: string) {
   if (!cookieCache) {
-    cookieCache = Object.fromEntries(
-      document.cookie.split('; ').map(c => c.split('='))
-    )
+    cookieCache = Object.fromEntries(document.cookie.split('; ').map((c) => c.split('=')));
   }
-  return cookieCache[name]
+  return cookieCache[name];
 }
 ```
 
@@ -59,12 +57,12 @@ If storage can change externally (another tab, server-set cookies), invalidate c
 
 ```typescript
 window.addEventListener('storage', (e) => {
-  if (e.key) storageCache.delete(e.key)
-})
+  if (e.key) storageCache.delete(e.key);
+});
 
 document.addEventListener('visibilitychange', () => {
   if (document.visibilityState === 'visible') {
-    storageCache.clear()
+    storageCache.clear();
   }
-})
+});
 ```

.agent/skills/vercel-react-best-practices/rules/js-combine-iterations.md

@@ -12,21 +12,21 @@ Multiple `.filter()` or `.map()` calls iterate the array multiple times. Combine
 **Incorrect (3 iterations):**
 
 ```typescript
-const admins = users.filter(u => u.isAdmin)
-const testers = users.filter(u => u.isTester)
-const inactive = users.filter(u => !u.isActive)
+const admins = users.filter((u) => u.isAdmin);
+const testers = users.filter((u) => u.isTester);
+const inactive = users.filter((u) => !u.isActive);
 ```
 
 **Correct (1 iteration):**
 
 ```typescript
-const admins: User[] = []
-const testers: User[] = []
-const inactive: User[] = []
+const admins: User[] = [];
+const testers: User[] = [];
+const inactive: User[] = [];
 
 for (const user of users) {
-  if (user.isAdmin) admins.push(user)
-  if (user.isTester) testers.push(user)
-  if (!user.isActive) inactive.push(user)
+  if (user.isAdmin) admins.push(user);
+  if (user.isTester) testers.push(user);
+  if (!user.isActive) inactive.push(user);
 }
 ```

.agent/skills/vercel-react-best-practices/rules/js-early-exit.md

@@ -13,22 +13,22 @@ Return early when result is determined to skip unnecessary processing.
 
 ```typescript
 function validateUsers(users: User[]) {
-  let hasError = false
-  let errorMessage = ''
-  
+  let hasError = false;
+  let errorMessage = '';
+
   for (const user of users) {
     if (!user.email) {
-      hasError = true
-      errorMessage = 'Email required'
+      hasError = true;
+      errorMessage = 'Email required';
     }
     if (!user.name) {
-      hasError = true
-      errorMessage = 'Name required'
+      hasError = true;
+      errorMessage = 'Name required';
     }
     // Continues checking all users even after error found
   }
-  
-  return hasError ? { valid: false, error: errorMessage } : { valid: true }
+
+  return hasError ? { valid: false, error: errorMessage } : { valid: true };
 }
 ```
 
@@ -38,13 +38,13 @@ function validateUsers(users: User[]) {
 function validateUsers(users: User[]) {
   for (const user of users) {
     if (!user.email) {
-      return { valid: false, error: 'Email required' }
+      return { valid: false, error: 'Email required' };
     }
     if (!user.name) {
-      return { valid: false, error: 'Name required' }
+      return { valid: false, error: 'Name required' };
     }
   }
 
-  return { valid: true }
+  return { valid: true };
 }
 ```

.agent/skills/vercel-react-best-practices/rules/js-hoist-regexp.md

@@ -39,7 +39,7 @@ function Highlighter({ text, query }: Props) {
 Global regex (`/g`) has mutable `lastIndex` state:
 
 ```typescript
-const regex = /foo/g
-regex.test('foo')  // true, lastIndex = 3
-regex.test('foo')  // false, lastIndex = 0
+const regex = /foo/g;
+regex.test('foo'); // true, lastIndex = 3
+regex.test('foo'); // false, lastIndex = 0
 ```

.agent/skills/vercel-react-best-practices/rules/js-index-maps.md

@@ -13,10 +13,10 @@ Multiple `.find()` calls by the same key should use a Map.
 
 ```typescript
 function processOrders(orders: Order[], users: User[]) {
-  return orders.map(order => ({
+  return orders.map((order) => ({
     ...order,
-    user: users.find(u => u.id === order.userId)
-  }))
+    user: users.find((u) => u.id === order.userId),
+  }));
 }
 ```
 
@@ -24,12 +24,12 @@ function processOrders(orders: Order[], users: User[]) {
 
 ```typescript
 function processOrders(orders: Order[], users: User[]) {
-  const userById = new Map(users.map(u => [u.id, u]))
+  const userById = new Map(users.map((u) => [u.id, u]));
 
-  return orders.map(order => ({
+  return orders.map((order) => ({
     ...order,
-    user: userById.get(order.userId)
-  }))
+    user: userById.get(order.userId),
+  }));
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/js-length-check-first.md

@@ -16,7 +16,7 @@ In real-world applications, this optimization is especially valuable when the co
 ```typescript
 function hasChanges(current: string[], original: string[]) {
   // Always sorts and joins, even when lengths differ
-  return current.sort().join() !== original.sort().join()
+  return current.sort().join() !== original.sort().join();
 }
 ```
 
@@ -28,21 +28,22 @@ Two O(n log n) sorts run even when `current.length` is 5 and `original.length` i
 function hasChanges(current: string[], original: string[]) {
   // Early return if lengths differ
   if (current.length !== original.length) {
-    return true
+    return true;
   }
   // Only sort when lengths match
-  const currentSorted = current.toSorted()
-  const originalSorted = original.toSorted()
+  const currentSorted = current.toSorted();
+  const originalSorted = original.toSorted();
   for (let i = 0; i < currentSorted.length; i++) {
     if (currentSorted[i] !== originalSorted[i]) {
-      return true
+      return true;
     }
   }
-  return false
+  return false;
 }
 ```
 
 This new approach is more efficient because:
+
 - It avoids the overhead of sorting and joining the arrays when lengths differ
 - It avoids consuming memory for the joined strings (especially important for large arrays)
 - It avoids mutating the original arrays

.agent/skills/vercel-react-best-practices/rules/js-min-max-loop.md

@@ -13,14 +13,14 @@ Finding the smallest or largest element only requires a single pass through the
 
 ```typescript
 interface Project {
-  id: string
-  name: string
-  updatedAt: number
+  id: string;
+  name: string;
+  updatedAt: number;
 }
 
 function getLatestProject(projects: Project[]) {
-  const sorted = [...projects].sort((a, b) => b.updatedAt - a.updatedAt)
-  return sorted[0]
+  const sorted = [...projects].sort((a, b) => b.updatedAt - a.updatedAt);
+  return sorted[0];
 }
 ```
 
@@ -30,8 +30,8 @@ Sorts the entire array just to find the maximum value.
 
 ```typescript
 function getOldestAndNewest(projects: Project[]) {
-  const sorted = [...projects].sort((a, b) => a.updatedAt - b.updatedAt)
-  return { oldest: sorted[0], newest: sorted[sorted.length - 1] }
+  const sorted = [...projects].sort((a, b) => a.updatedAt - b.updatedAt);
+  return { oldest: sorted[0], newest: sorted[sorted.length - 1] };
 }
 ```
 
@@ -41,31 +41,31 @@ Still sorts unnecessarily when only min/max are needed.
 
 ```typescript
 function getLatestProject(projects: Project[]) {
-  if (projects.length === 0) return null
-  
-  let latest = projects[0]
-  
+  if (projects.length === 0) return null;
+
+  let latest = projects[0];
+
   for (let i = 1; i < projects.length; i++) {
     if (projects[i].updatedAt > latest.updatedAt) {
-      latest = projects[i]
+      latest = projects[i];
     }
   }
-  
-  return latest
+
+  return latest;
 }
 
 function getOldestAndNewest(projects: Project[]) {
-  if (projects.length === 0) return { oldest: null, newest: null }
-  
-  let oldest = projects[0]
-  let newest = projects[0]
-  
+  if (projects.length === 0) return { oldest: null, newest: null };
+
+  let oldest = projects[0];
+  let newest = projects[0];
+
   for (let i = 1; i < projects.length; i++) {
-    if (projects[i].updatedAt < oldest.updatedAt) oldest = projects[i]
-    if (projects[i].updatedAt > newest.updatedAt) newest = projects[i]
+    if (projects[i].updatedAt < oldest.updatedAt) oldest = projects[i];
+    if (projects[i].updatedAt > newest.updatedAt) newest = projects[i];
   }
-  
-  return { oldest, newest }
+
+  return { oldest, newest };
 }
 ```
 
@@ -74,9 +74,9 @@ Single pass through the array, no copying, no sorting.
 **Alternative (Math.min/Math.max for small arrays):**
 
 ```typescript
-const numbers = [5, 2, 8, 1, 9]
-const min = Math.min(...numbers)
-const max = Math.max(...numbers)
+const numbers = [5, 2, 8, 1, 9];
+const min = Math.min(...numbers);
+const max = Math.max(...numbers);
 ```
 
 This works for small arrays, but can be slower or just throw an error for very large arrays due to spread operator limitations. Maximal array length is approximately 124000 in Chrome 143 and 638000 in Safari 18; exact numbers may vary - see [the fiddle](https://jsfiddle.net/qw1jabsx/4/). Use the loop approach for reliability.

.agent/skills/vercel-react-best-practices/rules/js-tosorted-immutable.md

@@ -46,7 +46,7 @@ function UserList({ users }: { users: User[] }) {
 
 ```typescript
 // Fallback for older browsers
-const sorted = [...items].sort((a, b) => a.value - b.value)
+const sorted = [...items].sort((a, b) => a.value - b.value);
 ```
 
 **Other immutable array methods:**

.agent/skills/vercel-react-best-practices/rules/rendering-activity.md

@@ -12,14 +12,14 @@ Use React's `<Activity>` to preserve state/DOM for expensive components that fre
 **Usage:**
 
 ```tsx
-import { Activity } from 'react'
+import { Activity } from 'react';
 
 function Dropdown({ isOpen }: Props) {
   return (
     <Activity mode={isOpen ? 'visible' : 'hidden'}>
       <ExpensiveMenu />
     </Activity>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rendering-animate-svg-wrapper.md

@@ -14,15 +14,10 @@ Many browsers don't have hardware acceleration for CSS3 animations on SVG elemen
 ```tsx
 function LoadingSpinner() {
   return (
-    <svg 
-      className="animate-spin"
-      width="24" 
-      height="24" 
-      viewBox="0 0 24 24"
-    >
+    <svg className="animate-spin" width="24" height="24" viewBox="0 0 24 24">
       <circle cx="12" cy="12" r="10" stroke="currentColor" />
     </svg>
-  )
+  );
 }
 ```
 
@@ -32,15 +27,11 @@ function LoadingSpinner() {
 function LoadingSpinner() {
   return (
     <div className="animate-spin">
-      <svg 
-        width="24" 
-        height="24" 
-        viewBox="0 0 24 24"
-      >
+      <svg width="24" height="24" viewBox="0 0 24 24">
         <circle cx="12" cy="12" r="10" stroke="currentColor" />
       </svg>
     </div>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rendering-conditional-render.md

@@ -13,11 +13,7 @@ Use explicit ternary operators (`? :`) instead of `&&` for conditional rendering
 
 ```tsx
 function Badge({ count }: { count: number }) {
-  return (
-    <div>
-      {count && <span className="badge">{count}</span>}
-    </div>
-  )
+  return <div>{count && <span className="badge">{count}</span>}</div>;
 }
 
 // When count = 0, renders: <div>0</div>
@@ -28,11 +24,7 @@ function Badge({ count }: { count: number }) {
 
 ```tsx
 function Badge({ count }: { count: number }) {
-  return (
-    <div>
-      {count > 0 ? <span className="badge">{count}</span> : null}
-    </div>
-  )
+  return <div>{count > 0 ? <span className="badge">{count}</span> : null}</div>;
 }
 
 // When count = 0, renders: <div></div>

.agent/skills/vercel-react-best-practices/rules/rendering-content-visibility.md

@@ -23,15 +23,15 @@ Apply `content-visibility: auto` to defer off-screen rendering.
 ```tsx
 function MessageList({ messages }: { messages: Message[] }) {
   return (
-    <div className="overflow-y-auto h-screen">
-      {messages.map(msg => (
+    <div className="h-screen overflow-y-auto">
+      {messages.map((msg) => (
         <div key={msg.id} className="message-item">
           <Avatar user={msg.author} />
           <div>{msg.content}</div>
         </div>
       ))}
     </div>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rendering-hoist-jsx.md

@@ -13,31 +13,21 @@ Extract static JSX outside components to avoid re-creation.
 
 ```tsx
 function LoadingSkeleton() {
-  return <div className="animate-pulse h-20 bg-gray-200" />
+  return <div className="h-20 animate-pulse bg-gray-200" />;
 }
 
 function Container() {
-  return (
-    <div>
-      {loading && <LoadingSkeleton />}
-    </div>
-  )
+  return <div>{loading && <LoadingSkeleton />}</div>;
 }
 ```
 
 **Correct (reuses same element):**
 
 ```tsx
-const loadingSkeleton = (
-  <div className="animate-pulse h-20 bg-gray-200" />
-)
+const loadingSkeleton = <div className="h-20 animate-pulse bg-gray-200" />;
 
 function Container() {
-  return (
-    <div>
-      {loading && loadingSkeleton}
-    </div>
-  )
+  return <div>{loading && loadingSkeleton}</div>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rendering-hydration-no-flicker.md

@@ -14,13 +14,9 @@ When rendering content that depends on client-side storage (localStorage, cookie
 ```tsx
 function ThemeWrapper({ children }: { children: ReactNode }) {
   // localStorage is not available on server - throws error
-  const theme = localStorage.getItem('theme') || 'light'
-  
-  return (
-    <div className={theme}>
-      {children}
-    </div>
-  )
+  const theme = localStorage.getItem('theme') || 'light';
+
+  return <div className={theme}>{children}</div>;
 }
 ```
 
@@ -30,21 +26,17 @@ Server-side rendering will fail because `localStorage` is undefined.
 
 ```tsx
 function ThemeWrapper({ children }: { children: ReactNode }) {
-  const [theme, setTheme] = useState('light')
-  
+  const [theme, setTheme] = useState('light');
+
   useEffect(() => {
     // Runs after hydration - causes visible flash
-    const stored = localStorage.getItem('theme')
+    const stored = localStorage.getItem('theme');
     if (stored) {
-      setTheme(stored)
+      setTheme(stored);
     }
-  }, [])
-  
-  return (
-    <div className={theme}>
-      {children}
-    </div>
-  )
+  }, []);
+
+  return <div className={theme}>{children}</div>;
 }
 ```
 
@@ -56,9 +48,7 @@ Component first renders with default value (`light`), then updates after hydrati
 function ThemeWrapper({ children }: { children: ReactNode }) {
   return (
     <>
-      <div id="theme-wrapper">
-        {children}
-      </div>
+      <div id="theme-wrapper">{children}</div>
       <script
         dangerouslySetInnerHTML={{
           __html: `
@@ -73,7 +63,7 @@ function ThemeWrapper({ children }: { children: ReactNode }) {
         }}
       />
     </>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rendering-hydration-suppress-warning.md

@@ -7,13 +7,13 @@ tags: rendering, hydration, ssr, nextjs
 
 ## Suppress Expected Hydration Mismatches
 
-In SSR frameworks (e.g., Next.js), some values are intentionally different on server vs client (random IDs, dates, locale/timezone formatting). For these *expected* mismatches, wrap the dynamic text in an element with `suppressHydrationWarning` to prevent noisy warnings. Do not use this to hide real bugs. Don’t overuse it.
+In SSR frameworks (e.g., Next.js), some values are intentionally different on server vs client (random IDs, dates, locale/timezone formatting). For these _expected_ mismatches, wrap the dynamic text in an element with `suppressHydrationWarning` to prevent noisy warnings. Do not use this to hide real bugs. Don’t overuse it.
 
 **Incorrect (known mismatch warnings):**
 
 ```tsx
 function Timestamp() {
-  return <span>{new Date().toLocaleString()}</span>
+  return <span>{new Date().toLocaleString()}</span>;
 }
 ```
 
@@ -21,10 +21,6 @@ function Timestamp() {
 
 ```tsx
 function Timestamp() {
-  return (
-    <span suppressHydrationWarning>
-      {new Date().toLocaleString()}
-    </span>
-  )
+  return <span suppressHydrationWarning>{new Date().toLocaleString()}</span>;
 }
 ```

.agent/skills/vercel-react-best-practices/rules/rendering-usetransition-loading.md

@@ -13,17 +13,17 @@ Use `useTransition` instead of manual `useState` for loading states. This provid
 
 ```tsx
 function SearchResults() {
-  const [query, setQuery] = useState('')
-  const [results, setResults] = useState([])
-  const [isLoading, setIsLoading] = useState(false)
+  const [query, setQuery] = useState('');
+  const [results, setResults] = useState([]);
+  const [isLoading, setIsLoading] = useState(false);
 
   const handleSearch = async (value: string) => {
-    setIsLoading(true)
-    setQuery(value)
-    const data = await fetchResults(value)
-    setResults(data)
-    setIsLoading(false)
-  }
+    setIsLoading(true);
+    setQuery(value);
+    const data = await fetchResults(value);
+    setResults(data);
+    setIsLoading(false);
+  };
 
   return (
     <>
@@ -31,29 +31,29 @@ function SearchResults() {
       {isLoading && <Spinner />}
       <ResultsList results={results} />
     </>
-  )
+  );
 }
 ```
 
 **Correct (useTransition with built-in pending state):**
 
 ```tsx
-import { useTransition, useState } from 'react'
+import { useTransition, useState } from 'react';
 
 function SearchResults() {
-  const [query, setQuery] = useState('')
-  const [results, setResults] = useState([])
-  const [isPending, startTransition] = useTransition()
+  const [query, setQuery] = useState('');
+  const [results, setResults] = useState([]);
+  const [isPending, startTransition] = useTransition();
 
   const handleSearch = (value: string) => {
-    setQuery(value) // Update input immediately
-    
+    setQuery(value); // Update input immediately
+
     startTransition(async () => {
       // Fetch and update results
-      const data = await fetchResults(value)
-      setResults(data)
-    })
-  }
+      const data = await fetchResults(value);
+      setResults(data);
+    });
+  };
 
   return (
     <>
@@ -61,7 +61,7 @@ function SearchResults() {
       {isPending && <Spinner />}
       <ResultsList results={results} />
     </>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-defer-reads.md

@@ -13,14 +13,14 @@ Don't subscribe to dynamic state (searchParams, localStorage) if you only read i
 
 ```tsx
 function ShareButton({ chatId }: { chatId: string }) {
-  const searchParams = useSearchParams()
+  const searchParams = useSearchParams();
 
   const handleShare = () => {
-    const ref = searchParams.get('ref')
-    shareChat(chatId, { ref })
-  }
+    const ref = searchParams.get('ref');
+    shareChat(chatId, { ref });
+  };
 
-  return <button onClick={handleShare}>Share</button>
+  return <button onClick={handleShare}>Share</button>;
 }
 ```
 
@@ -29,11 +29,11 @@ function ShareButton({ chatId }: { chatId: string }) {
 ```tsx
 function ShareButton({ chatId }: { chatId: string }) {
   const handleShare = () => {
-    const params = new URLSearchParams(window.location.search)
-    const ref = params.get('ref')
-    shareChat(chatId, { ref })
-  }
+    const params = new URLSearchParams(window.location.search);
+    const ref = params.get('ref');
+    shareChat(chatId, { ref });
+  };
 
-  return <button onClick={handleShare}>Share</button>
+  return <button onClick={handleShare}>Share</button>;
 }
 ```

.agent/skills/vercel-react-best-practices/rules/rerender-dependencies.md

@@ -13,16 +13,16 @@ Specify primitive dependencies instead of objects to minimize effect re-runs.
 
 ```tsx
 useEffect(() => {
-  console.log(user.id)
-}, [user])
+  console.log(user.id);
+}, [user]);
 ```
 
 **Correct (re-runs only when id changes):**
 
 ```tsx
 useEffect(() => {
-  console.log(user.id)
-}, [user.id])
+  console.log(user.id);
+}, [user.id]);
 ```
 
 **For derived state, compute outside effect:**
@@ -31,15 +31,15 @@ useEffect(() => {
 // Incorrect: runs on width=767, 766, 765...
 useEffect(() => {
   if (width < 768) {
-    enableMobileMode()
+    enableMobileMode();
   }
-}, [width])
+}, [width]);
 
 // Correct: runs only on boolean transition
-const isMobile = width < 768
+const isMobile = width < 768;
 useEffect(() => {
   if (isMobile) {
-    enableMobileMode()
+    enableMobileMode();
   }
-}, [isMobile])
+}, [isMobile]);
 ```

.agent/skills/vercel-react-best-practices/rules/rerender-derived-state-no-effect.md

@@ -13,15 +13,15 @@ If a value can be computed from current props/state, do not store it in state or
 
 ```tsx
 function Form() {
-  const [firstName, setFirstName] = useState('First')
-  const [lastName, setLastName] = useState('Last')
-  const [fullName, setFullName] = useState('')
+  const [firstName, setFirstName] = useState('First');
+  const [lastName, setLastName] = useState('Last');
+  const [fullName, setFullName] = useState('');
 
   useEffect(() => {
-    setFullName(firstName + ' ' + lastName)
-  }, [firstName, lastName])
+    setFullName(firstName + ' ' + lastName);
+  }, [firstName, lastName]);
 
-  return <p>{fullName}</p>
+  return <p>{fullName}</p>;
 }
 ```
 
@@ -29,11 +29,11 @@ function Form() {
 
 ```tsx
 function Form() {
-  const [firstName, setFirstName] = useState('First')
-  const [lastName, setLastName] = useState('Last')
-  const fullName = firstName + ' ' + lastName
+  const [firstName, setFirstName] = useState('First');
+  const [lastName, setLastName] = useState('Last');
+  const fullName = firstName + ' ' + lastName;
 
-  return <p>{fullName}</p>
+  return <p>{fullName}</p>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-derived-state.md

@@ -13,9 +13,9 @@ Subscribe to derived boolean state instead of continuous values to reduce re-ren
 
 ```tsx
 function Sidebar() {
-  const width = useWindowWidth()  // updates continuously
-  const isMobile = width < 768
-  return <nav className={isMobile ? 'mobile' : 'desktop'} />
+  const width = useWindowWidth(); // updates continuously
+  const isMobile = width < 768;
+  return <nav className={isMobile ? 'mobile' : 'desktop'} />;
 }
 ```
 
@@ -23,7 +23,7 @@ function Sidebar() {
 
 ```tsx
 function Sidebar() {
-  const isMobile = useMediaQuery('(max-width: 767px)')
-  return <nav className={isMobile ? 'mobile' : 'desktop'} />
+  const isMobile = useMediaQuery('(max-width: 767px)');
+  return <nav className={isMobile ? 'mobile' : 'desktop'} />;
 }
 ```

.agent/skills/vercel-react-best-practices/rules/rerender-functional-setstate.md

@@ -13,19 +13,22 @@ When updating state based on the current state value, use the functional update
 
 ```tsx
 function TodoList() {
-  const [items, setItems] = useState(initialItems)
-  
+  const [items, setItems] = useState(initialItems);
+
   // Callback must depend on items, recreated on every items change
-  const addItems = useCallback((newItems: Item[]) => {
-    setItems([...items, ...newItems])
-  }, [items])  // ❌ items dependency causes recreations
-  
+  const addItems = useCallback(
+    (newItems: Item[]) => {
+      setItems([...items, ...newItems]);
+    },
+    [items],
+  ); // ❌ items dependency causes recreations
+
   // Risk of stale closure if dependency is forgotten
   const removeItem = useCallback((id: string) => {
-    setItems(items.filter(item => item.id !== id))
-  }, [])  // ❌ Missing items dependency - will use stale items!
-  
-  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
+    setItems(items.filter((item) => item.id !== id));
+  }, []); // ❌ Missing items dependency - will use stale items!
+
+  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />;
 }
 ```
 
@@ -35,19 +38,19 @@ The first callback is recreated every time `items` changes, which can cause chil
 
 ```tsx
 function TodoList() {
-  const [items, setItems] = useState(initialItems)
-  
+  const [items, setItems] = useState(initialItems);
+
   // Stable callback, never recreated
   const addItems = useCallback((newItems: Item[]) => {
-    setItems(curr => [...curr, ...newItems])
-  }, [])  // ✅ No dependencies needed
-  
+    setItems((curr) => [...curr, ...newItems]);
+  }, []); // ✅ No dependencies needed
+
   // Always uses latest state, no stale closure risk
   const removeItem = useCallback((id: string) => {
-    setItems(curr => curr.filter(item => item.id !== id))
-  }, [])  // ✅ Safe and stable
-  
-  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
+    setItems((curr) => curr.filter((item) => item.id !== id));
+  }, []); // ✅ Safe and stable
+
+  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-lazy-state-init.md

@@ -14,20 +14,18 @@ Pass a function to `useState` for expensive initial values. Without the function
 ```tsx
 function FilteredList({ items }: { items: Item[] }) {
   // buildSearchIndex() runs on EVERY render, even after initialization
-  const [searchIndex, setSearchIndex] = useState(buildSearchIndex(items))
-  const [query, setQuery] = useState('')
-  
+  const [searchIndex, setSearchIndex] = useState(buildSearchIndex(items));
+  const [query, setQuery] = useState('');
+
   // When query changes, buildSearchIndex runs again unnecessarily
-  return <SearchResults index={searchIndex} query={query} />
+  return <SearchResults index={searchIndex} query={query} />;
 }
 
 function UserProfile() {
   // JSON.parse runs on every render
-  const [settings, setSettings] = useState(
-    JSON.parse(localStorage.getItem('settings') || '{}')
-  )
-  
-  return <SettingsForm settings={settings} onChange={setSettings} />
+  const [settings, setSettings] = useState(JSON.parse(localStorage.getItem('settings') || '{}'));
+
+  return <SettingsForm settings={settings} onChange={setSettings} />;
 }
 ```
 
@@ -36,20 +34,20 @@ function UserProfile() {
 ```tsx
 function FilteredList({ items }: { items: Item[] }) {
   // buildSearchIndex() runs ONLY on initial render
-  const [searchIndex, setSearchIndex] = useState(() => buildSearchIndex(items))
-  const [query, setQuery] = useState('')
-  
-  return <SearchResults index={searchIndex} query={query} />
+  const [searchIndex, setSearchIndex] = useState(() => buildSearchIndex(items));
+  const [query, setQuery] = useState('');
+
+  return <SearchResults index={searchIndex} query={query} />;
 }
 
 function UserProfile() {
   // JSON.parse runs only on initial render
   const [settings, setSettings] = useState(() => {
-    const stored = localStorage.getItem('settings')
-    return stored ? JSON.parse(stored) : {}
-  })
-  
-  return <SettingsForm settings={settings} onChange={setSettings} />
+    const stored = localStorage.getItem('settings');
+    return stored ? JSON.parse(stored) : {};
+  });
+
+  return <SettingsForm settings={settings} onChange={setSettings} />;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-memo-with-default-value.md

@@ -1,10 +1,8 @@
 ---
-
 title: Extract Default Non-primitive Parameter Value from Memoized Component to Constant
 impact: MEDIUM
 impactDescription: restores memoization by using a constant for default value
 tags: rerender, memo, optimization
-
 ---
 
 ## Extract Default Non-primitive Parameter Value from Memoized Component to Constant

.agent/skills/vercel-react-best-practices/rules/rerender-memo.md

@@ -14,12 +14,12 @@ Extract expensive work into memoized components to enable early returns before c
 ```tsx
 function Profile({ user, loading }: Props) {
   const avatar = useMemo(() => {
-    const id = computeAvatarId(user)
-    return <Avatar id={id} />
-  }, [user])
+    const id = computeAvatarId(user);
+    return <Avatar id={id} />;
+  }, [user]);
 
-  if (loading) return <Skeleton />
-  return <div>{avatar}</div>
+  if (loading) return <Skeleton />;
+  return <div>{avatar}</div>;
 }
 ```
 
@@ -27,17 +27,17 @@ function Profile({ user, loading }: Props) {
 
 ```tsx
 const UserAvatar = memo(function UserAvatar({ user }: { user: User }) {
-  const id = useMemo(() => computeAvatarId(user), [user])
-  return <Avatar id={id} />
-})
+  const id = useMemo(() => computeAvatarId(user), [user]);
+  return <Avatar id={id} />;
+});
 
 function Profile({ user, loading }: Props) {
-  if (loading) return <Skeleton />
+  if (loading) return <Skeleton />;
   return (
     <div>
       <UserAvatar user={user} />
     </div>
-  )
+  );
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-move-effect-to-event.md

@@ -13,17 +13,17 @@ If a side effect is triggered by a specific user action (submit, click, drag), r
 
 ```tsx
 function Form() {
-  const [submitted, setSubmitted] = useState(false)
-  const theme = useContext(ThemeContext)
+  const [submitted, setSubmitted] = useState(false);
+  const theme = useContext(ThemeContext);
 
   useEffect(() => {
     if (submitted) {
-      post('/api/register')
-      showToast('Registered', theme)
+      post('/api/register');
+      showToast('Registered', theme);
     }
-  }, [submitted, theme])
+  }, [submitted, theme]);
 
-  return <button onClick={() => setSubmitted(true)}>Submit</button>
+  return <button onClick={() => setSubmitted(true)}>Submit</button>;
 }
 ```
 
@@ -31,14 +31,14 @@ function Form() {
 
 ```tsx
 function Form() {
-  const theme = useContext(ThemeContext)
+  const theme = useContext(ThemeContext);
 
   function handleSubmit() {
-    post('/api/register')
-    showToast('Registered', theme)
+    post('/api/register');
+    showToast('Registered', theme);
   }
 
-  return <button onClick={handleSubmit}>Submit</button>
+  return <button onClick={handleSubmit}>Submit</button>;
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/rerender-simple-expression-in-memo.md

@@ -15,10 +15,10 @@ Calling `useMemo` and comparing hook dependencies may consume more resources tha
 ```tsx
 function Header({ user, notifications }: Props) {
   const isLoading = useMemo(() => {
-    return user.isLoading || notifications.isLoading
-  }, [user.isLoading, notifications.isLoading])
+    return user.isLoading || notifications.isLoading;
+  }, [user.isLoading, notifications.isLoading]);
 
-  if (isLoading) return <Skeleton />
+  if (isLoading) return <Skeleton />;
   // return some markup
 }
 ```
@@ -27,9 +27,9 @@ function Header({ user, notifications }: Props) {
 
 ```tsx
 function Header({ user, notifications }: Props) {
-  const isLoading = user.isLoading || notifications.isLoading
+  const isLoading = user.isLoading || notifications.isLoading;
 
-  if (isLoading) return <Skeleton />
+  if (isLoading) return <Skeleton />;
   // return some markup
 }
 ```

.agent/skills/vercel-react-best-practices/rules/rerender-transitions.md

@@ -13,28 +13,28 @@ Mark frequent, non-urgent state updates as transitions to maintain UI responsive
 
 ```tsx
 function ScrollTracker() {
-  const [scrollY, setScrollY] = useState(0)
+  const [scrollY, setScrollY] = useState(0);
   useEffect(() => {
-    const handler = () => setScrollY(window.scrollY)
-    window.addEventListener('scroll', handler, { passive: true })
-    return () => window.removeEventListener('scroll', handler)
-  }, [])
+    const handler = () => setScrollY(window.scrollY);
+    window.addEventListener('scroll', handler, { passive: true });
+    return () => window.removeEventListener('scroll', handler);
+  }, []);
 }
 ```
 
 **Correct (non-blocking updates):**
 
 ```tsx
-import { startTransition } from 'react'
+import { startTransition } from 'react';
 
 function ScrollTracker() {
-  const [scrollY, setScrollY] = useState(0)
+  const [scrollY, setScrollY] = useState(0);
   useEffect(() => {
     const handler = () => {
-      startTransition(() => setScrollY(window.scrollY))
-    }
-    window.addEventListener('scroll', handler, { passive: true })
-    return () => window.removeEventListener('scroll', handler)
-  }, [])
+      startTransition(() => setScrollY(window.scrollY));
+    };
+    window.addEventListener('scroll', handler, { passive: true });
+    return () => window.removeEventListener('scroll', handler);
+  }, []);
 }
 ```

.agent/skills/vercel-react-best-practices/rules/rerender-use-ref-transient-values.md

@@ -13,13 +13,13 @@ When a value changes frequently and you don't want a re-render on every update (
 
 ```tsx
 function Tracker() {
-  const [lastX, setLastX] = useState(0)
+  const [lastX, setLastX] = useState(0);
 
   useEffect(() => {
-    const onMove = (e: MouseEvent) => setLastX(e.clientX)
-    window.addEventListener('mousemove', onMove)
-    return () => window.removeEventListener('mousemove', onMove)
-  }, [])
+    const onMove = (e: MouseEvent) => setLastX(e.clientX);
+    window.addEventListener('mousemove', onMove);
+    return () => window.removeEventListener('mousemove', onMove);
+  }, []);
 
   return (
     <div
@@ -32,7 +32,7 @@ function Tracker() {
         background: 'black',
       }}
     />
-  )
+  );
 }
 ```
 
@@ -40,20 +40,20 @@ function Tracker() {
 
 ```tsx
 function Tracker() {
-  const lastXRef = useRef(0)
-  const dotRef = useRef<HTMLDivElement>(null)
+  const lastXRef = useRef(0);
+  const dotRef = useRef<HTMLDivElement>(null);
 
   useEffect(() => {
     const onMove = (e: MouseEvent) => {
-      lastXRef.current = e.clientX
-      const node = dotRef.current
+      lastXRef.current = e.clientX;
+      const node = dotRef.current;
       if (node) {
-        node.style.transform = `translateX(${e.clientX}px)`
+        node.style.transform = `translateX(${e.clientX}px)`;
       }
-    }
-    window.addEventListener('mousemove', onMove)
-    return () => window.removeEventListener('mousemove', onMove)
-  }, [])
+    };
+    window.addEventListener('mousemove', onMove);
+    return () => window.removeEventListener('mousemove', onMove);
+  }, []);
 
   return (
     <div
@@ -68,6 +68,6 @@ function Tracker() {
         transform: 'translateX(0px)',
       }}
     />
-  )
+  );
 }
 ```

.agent/skills/vercel-react-best-practices/rules/server-after-nonblocking.md

@@ -12,46 +12,46 @@ Use Next.js's `after()` to schedule work that should execute after a response is
 **Incorrect (blocks response):**
 
 ```tsx
-import { logUserAction } from '@/app/utils'
+import { logUserAction } from '@/app/utils';
 
 export async function POST(request: Request) {
   // Perform mutation
-  await updateDatabase(request)
-  
+  await updateDatabase(request);
+
   // Logging blocks the response
-  const userAgent = request.headers.get('user-agent') || 'unknown'
-  await logUserAction({ userAgent })
-  
+  const userAgent = request.headers.get('user-agent') || 'unknown';
+  await logUserAction({ userAgent });
+
   return new Response(JSON.stringify({ status: 'success' }), {
     status: 200,
-    headers: { 'Content-Type': 'application/json' }
-  })
+    headers: { 'Content-Type': 'application/json' },
+  });
 }
 ```
 
 **Correct (non-blocking):**
 
 ```tsx
-import { after } from 'next/server'
-import { headers, cookies } from 'next/headers'
-import { logUserAction } from '@/app/utils'
+import { after } from 'next/server';
+import { headers, cookies } from 'next/headers';
+import { logUserAction } from '@/app/utils';
 
 export async function POST(request: Request) {
   // Perform mutation
-  await updateDatabase(request)
-  
+  await updateDatabase(request);
+
   // Log after response is sent
   after(async () => {
-    const userAgent = (await headers()).get('user-agent') || 'unknown'
-    const sessionCookie = (await cookies()).get('session-id')?.value || 'anonymous'
-    
-    logUserAction({ sessionCookie, userAgent })
-  })
-  
+    const userAgent = (await headers()).get('user-agent') || 'unknown';
+    const sessionCookie = (await cookies()).get('session-id')?.value || 'anonymous';
+
+    logUserAction({ sessionCookie, userAgent });
+  });
+
   return new Response(JSON.stringify({ status: 'success' }), {
     status: 200,
-    headers: { 'Content-Type': 'application/json' }
-  })
+    headers: { 'Content-Type': 'application/json' },
+  });
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/server-auth-actions.md

@@ -16,80 +16,80 @@ Next.js documentation explicitly states: "Treat Server Actions with the same sec
 **Incorrect (no authentication check):**
 
 ```typescript
-'use server'
+'use server';
 
 export async function deleteUser(userId: string) {
   // Anyone can call this! No auth check
-  await db.user.delete({ where: { id: userId } })
-  return { success: true }
+  await db.user.delete({ where: { id: userId } });
+  return { success: true };
 }
 ```
 
 **Correct (authentication inside the action):**
 
 ```typescript
-'use server'
+'use server';
 
-import { verifySession } from '@/lib/auth'
-import { unauthorized } from '@/lib/errors'
+import { verifySession } from '@/lib/auth';
+import { unauthorized } from '@/lib/errors';
 
 export async function deleteUser(userId: string) {
   // Always check auth inside the action
-  const session = await verifySession()
-  
+  const session = await verifySession();
+
   if (!session) {
-    throw unauthorized('Must be logged in')
+    throw unauthorized('Must be logged in');
   }
-  
+
   // Check authorization too
   if (session.user.role !== 'admin' && session.user.id !== userId) {
-    throw unauthorized('Cannot delete other users')
+    throw unauthorized('Cannot delete other users');
   }
-  
-  await db.user.delete({ where: { id: userId } })
-  return { success: true }
+
+  await db.user.delete({ where: { id: userId } });
+  return { success: true };
 }
 ```
 
 **With input validation:**
 
 ```typescript
-'use server'
+'use server';
 
-import { verifySession } from '@/lib/auth'
-import { z } from 'zod'
+import { verifySession } from '@/lib/auth';
+import { z } from 'zod';
 
 const updateProfileSchema = z.object({
   userId: z.string().uuid(),
   name: z.string().min(1).max(100),
-  email: z.string().email()
-})
+  email: z.string().email(),
+});
 
 export async function updateProfile(data: unknown) {
   // Validate input first
-  const validated = updateProfileSchema.parse(data)
-  
+  const validated = updateProfileSchema.parse(data);
+
   // Then authenticate
-  const session = await verifySession()
+  const session = await verifySession();
   if (!session) {
-    throw new Error('Unauthorized')
+    throw new Error('Unauthorized');
   }
-  
+
   // Then authorize
   if (session.user.id !== validated.userId) {
-    throw new Error('Can only update own profile')
+    throw new Error('Can only update own profile');
   }
-  
+
   // Finally perform the mutation
   await db.user.update({
     where: { id: validated.userId },
     data: {
       name: validated.name,
-      email: validated.email
-    }
-  })
-  
-  return { success: true }
+      email: validated.email,
+    },
+  });
+
+  return { success: true };
 }
 ```
 

.agent/skills/vercel-react-best-practices/rules/server-cache-lru.md

@@ -12,20 +12,20 @@ tags: server, cache, lru, cross-request
 **Implementation:**
 
 ```typescript
-import { LRUCache } from 'lru-cache'
+import { LRUCache } from 'lru-cache';
 
 const cache = new LRUCache<string, any>({
   max: 1000,
-  ttl: 5 * 60 * 1000  // 5 minutes
-})
+  ttl: 5 * 60 * 1000, // 5 minutes
+});
 
 export async function getUser(id: string) {
-  const cached = cache.get(id)
-  if (cached) return cached
+  const cached = cache.get(id);
+  if (cached) return cached;
 
-  const user = await db.user.findUnique({ where: { id } })
-  cache.set(id, user)
-  return user
+  const user = await db.user.findUnique({ where: { id } });
+  cache.set(id, user);
+  return user;
 }
 
 // Request 1: DB query, result cached

.agent/skills/vercel-react-best-practices/rules/server-cache-react.md

@@ -12,15 +12,15 @@ Use `React.cache()` for server-side request deduplication. Authentication and da
 **Usage:**
 
 ```typescript
-import { cache } from 'react'
+import { cache } from 'react';
 
 export const getCurrentUser = cache(async () => {
-  const session = await auth()
-  if (!session?.user?.id) return null
+  const session = await auth();
+  if (!session?.user?.id) return null;
   return await db.user.findUnique({
-    where: { id: session.user.id }
-  })
-})
+    where: { id: session.user.id },
+  });
+});
 ```
 
 Within a single request, multiple calls to `getCurrentUser()` execute the query only once.
@@ -33,32 +33,32 @@ Within a single request, multiple calls to `getCurrentUser()` execute the query
 
 ```typescript
 const getUser = cache(async (params: { uid: number }) => {
-  return await db.user.findUnique({ where: { id: params.uid } })
-})
+  return await db.user.findUnique({ where: { id: params.uid } });
+});
 
 // Each call creates new object, never hits cache
-getUser({ uid: 1 })
-getUser({ uid: 1 })  // Cache miss, runs query again
+getUser({ uid: 1 });
+getUser({ uid: 1 }); // Cache miss, runs query again
 ```
 
 **Correct (cache hit):**
 
 ```typescript
 const getUser = cache(async (uid: number) => {
-  return await db.user.findUnique({ where: { id: uid } })
-})
+  return await db.user.findUnique({ where: { id: uid } });
+});
 
 // Primitive args use value equality
-getUser(1)
-getUser(1)  // Cache hit, returns cached result
+getUser(1);
+getUser(1); // Cache hit, returns cached result
 ```
 
 If you must pass objects, pass the same reference:
 
 ```typescript
-const params = { uid: 1 }
-getUser(params)  // Query runs
-getUser(params)  // Cache hit (same reference)
+const params = { uid: 1 };
+getUser(params); // Query runs
+getUser(params); // Cache hit (same reference)
 ```
 
 **Next.js-Specific Note:**

.agent/skills/vercel-react-best-practices/rules/server-dedup-props.md

@@ -22,11 +22,11 @@ RSC→client serialization deduplicates by object reference, not value. Same ref
 
 ```tsx
 // RSC: send once
-<ClientList usernames={usernames} />
+<ClientList usernames={usernames} />;
 
 // Client: transform there
-'use client'
-const sorted = useMemo(() => [...usernames].sort(), [usernames])
+('use client');
+const sorted = useMemo(() => [...usernames].sort(), [usernames]);
 ```
 
 **Nested deduplication behavior:**

.agent/skills/vercel-react-best-practices/rules/server-parallel-fetching.md

@@ -13,18 +13,18 @@ React Server Components execute sequentially within a tree. Restructure with com
 
 ```tsx
 export default async function Page() {
-  const header = await fetchHeader()
+  const header = await fetchHeader();
   return (
     <div>
       <div>{header}</div>
       <Sidebar />
     </div>
-  )
+  );
 }
 
 async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
+  const items = await fetchSidebarItems();
+  return <nav>{items.map(renderItem)}</nav>;
 }
 ```
 
@@ -32,13 +32,13 @@ async function Sidebar() {
 
 ```tsx
 async function Header() {
-  const data = await fetchHeader()
-  return <div>{data}</div>
+  const data = await fetchHeader();
+  return <div>{data}</div>;
 }
 
 async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
+  const items = await fetchSidebarItems();
+  return <nav>{items.map(renderItem)}</nav>;
 }
 
 export default function Page() {
@@ -47,7 +47,7 @@ export default function Page() {
       <Header />
       <Sidebar />
     </div>
-  )
+  );
 }
 ```
 
@@ -55,13 +55,13 @@ export default function Page() {
 
 ```tsx
 async function Header() {
-  const data = await fetchHeader()
-  return <div>{data}</div>
+  const data = await fetchHeader();
+  return <div>{data}</div>;
 }
 
 async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
+  const items = await fetchSidebarItems();
+  return <nav>{items.map(renderItem)}</nav>;
 }
 
 function Layout({ children }: { children: ReactNode }) {
@@ -70,7 +70,7 @@ function Layout({ children }: { children: ReactNode }) {
       <Header />
       {children}
     </div>
-  )
+  );
 }
 
 export default function Page() {
@@ -78,6 +78,6 @@ export default function Page() {
     <Layout>
       <Sidebar />
     </Layout>
-  )
+  );
 }
 ```

.agent/skills/vercel-react-best-practices/rules/server-serialization.md

@@ -13,13 +13,13 @@ The React Server/Client boundary serializes all object properties into strings a
 
 ```tsx
 async function Page() {
-  const user = await fetchUser()  // 50 fields
-  return <Profile user={user} />
+  const user = await fetchUser(); // 50 fields
+  return <Profile user={user} />;
 }
 
-'use client'
+('use client');
 function Profile({ user }: { user: User }) {
-  return <div>{user.name}</div>  // uses 1 field
+  return <div>{user.name}</div>; // uses 1 field
 }
 ```
 
@@ -27,12 +27,12 @@ function Profile({ user }: { user: User }) {
 
 ```tsx
 async function Page() {
-  const user = await fetchUser()
-  return <Profile name={user.name} />
+  const user = await fetchUser();
+  return <Profile name={user.name} />;
 }
 
-'use client'
+('use client');
 function Profile({ name }: { name: string }) {
-  return <div>{name}</div>
+  return <div>{name}</div>;
 }
 ```

.agent/skills/web-design-guidelines/SKILL.md

@@ -3,7 +3,7 @@ name: web-design-guidelines
 description: Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
 metadata:
   author: vercel
-  version: "1.0.0"
+  version: '1.0.0'
   argument-hint: <file-or-pattern>
 ---
 
@@ -31,6 +31,7 @@ Use WebFetch to retrieve the latest rules. The fetched content contains all the
 ## Usage
 
 When a user provides a file or pattern argument:
+
 1. Fetch guidelines from the source URL above
 2. Read the specified files
 3. Apply all rules from the fetched guidelines

.agent/workflows/opsx-apply.md

@@ -18,9 +18,11 @@ Implement tasks from an OpenSpec change.
    Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
 
 2. **Check status to understand the schema**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand:
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
@@ -132,6 +134,7 @@ What would you like to do?
 ```
 
 **Guardrails**
+
 - Keep going through tasks until done or blocked
 - Always read context files before starting (from the apply instructions output)
 - If task is ambiguous, pause and ask before implementing

.agent/workflows/opsx-archive.md

@@ -61,6 +61,7 @@ Archive a completed change in the experimental workflow.
 5. **Perform the archive**
 
    Create the archive directory if it doesn't exist:
+
    ```bash
    mkdir -p openspec/changes/archive
    ```
@@ -145,6 +146,7 @@ Target archive directory already exists.
 ```
 
 **Guardrails**
+
 - Always prompt for change selection if not provided
 - Use artifact graph (openspec status --json) for completion checking
 - Don't block archive on warnings - just inform and confirm

.agent/workflows/opsx-bulk-archive.md

@@ -30,16 +30,16 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    For each selected change, collect:
 
    a. **Artifact status** - Run `openspec status --change "<name>" --json`
-      - Parse `schemaName` and `artifacts` list
-      - Note which artifacts are `done` vs other states
+   - Parse `schemaName` and `artifacts` list
+   - Note which artifacts are `done` vs other states
 
    b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
-      - Count `- [ ]` (incomplete) vs `- [x]` (complete)
-      - If no tasks file exists, note as "No tasks"
+   - Count `- [ ]` (incomplete) vs `- [x]` (complete)
+   - If no tasks file exists, note as "No tasks"
 
    c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
-      - List which capability specs exist
-      - For each, extract requirement names (lines matching `### Requirement: <name>`)
+   - List which capability specs exist
+   - For each, extract requirement names (lines matching `### Requirement: <name>`)
 
 4. **Detect spec conflicts**
 
@@ -59,18 +59,18 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
 
    b. **Search the codebase** for implementation evidence:
-      - Look for code implementing requirements from each delta spec
-      - Check for related files, functions, or tests
+   - Look for code implementing requirements from each delta spec
+   - Check for related files, functions, or tests
 
    c. **Determine resolution**:
-      - If only one change is actually implemented -> sync that one's specs
-      - If both implemented -> apply in chronological order (older first, newer overwrites)
-      - If neither implemented -> skip spec sync, warn user
+   - If only one change is actually implemented -> sync that one's specs
+   - If both implemented -> apply in chronological order (older first, newer overwrites)
+   - If neither implemented -> skip spec sync, warn user
 
    d. **Record resolution** for each conflict:
-      - Which change's specs to apply
-      - In what order (if both)
-      - Rationale (what was found in codebase)
+   - Which change's specs to apply
+   - In what order (if both)
+   - Rationale (what was found in codebase)
 
 6. **Show consolidated status table**
 
@@ -86,12 +86,14 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    For conflicts, show the resolution:
+
    ```
    * Conflict resolution:
      - auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
    ```
 
    For incomplete changes, show warnings:
+
    ```
    Warnings:
    - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
@@ -100,7 +102,6 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 7. **Confirm batch operation**
 
    Use **AskUserQuestion tool** with a single confirmation:
-
    - "Archive N changes?" with options based on status
    - Options might include:
      - "Archive all N changes"
@@ -114,20 +115,21 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    Process changes in the determined order (respecting conflict resolution):
 
    a. **Sync specs** if delta specs exist:
-      - Use the openspec-sync-specs approach (agent-driven intelligent merge)
-      - For conflicts, apply in resolved order
-      - Track if sync was done
+   - Use the openspec-sync-specs approach (agent-driven intelligent merge)
+   - For conflicts, apply in resolved order
+   - Track if sync was done
 
    b. **Perform the archive**:
-      ```bash
-      mkdir -p openspec/changes/archive
-      mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
-      ```
+
+   ```bash
+   mkdir -p openspec/changes/archive
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
 
    c. **Track outcome** for each change:
-      - Success: archived successfully
-      - Failed: error during archive (record error)
-      - Skipped: user chose not to archive (if applicable)
+   - Success: archived successfully
+   - Failed: error during archive (record error)
+   - Skipped: user chose not to archive (if applicable)
 
 9. **Display summary**
 
@@ -150,6 +152,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    If any failures:
+
    ```
    Failed 1 change:
    - some-change: Archive directory already exists
@@ -158,6 +161,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 **Conflict Resolution Examples**
 
 Example 1: Only one implemented
+
 ```
 Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
 
@@ -173,6 +177,7 @@ Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
 ```
 
 Example 2: Both implemented
+
 ```
 Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
 
@@ -226,6 +231,7 @@ No active changes found. Use `/opsx:new` to create a new change.
 ```
 
 **Guardrails**
+
 - Allow any number of changes (1+ is fine, 2+ is the typical use case)
 - Always prompt for selection, never auto-select
 - Detect spec conflicts early and resolve by checking codebase

.agent/workflows/opsx-continue.md

@@ -23,9 +23,11 @@ Continue working on a change by creating the next artifact.
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
 2. **Check current status**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand current state. The response includes:
    - `schemaName`: The workflow schema being used (e.g., "spec-driven")
    - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
@@ -33,7 +35,7 @@ Continue working on a change by creating the next artifact.
 
 3. **Act based on status**:
 
-   ---
+   ***
 
    **If all artifacts are complete (`isComplete: true`)**:
    - Congratulate the user
@@ -41,7 +43,7 @@ Continue working on a change by creating the next artifact.
    - Suggest: "All artifacts created! You can now implement this change with `/opsx:apply` or archive it with `/opsx:archive`."
    - STOP
 
-   ---
+   ***
 
    **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
    - Pick the FIRST artifact with `status: "ready"` from the status output
@@ -64,7 +66,7 @@ Continue working on a change by creating the next artifact.
    - Show what was created and what's now unlocked
    - STOP after creating ONE artifact
 
-   ---
+   ***
 
    **If no artifacts are ready (all blocked)**:
    - This shouldn't happen with a valid schema
@@ -78,6 +80,7 @@ Continue working on a change by creating the next artifact.
 **Output**
 
 After each invocation, show:
+
 - Which artifact was created
 - Schema workflow being used
 - Current progress (N/M complete)
@@ -91,6 +94,7 @@ The artifact types and their purpose depend on the schema. Use the `instruction`
 Common artifact patterns:
 
 **spec-driven schema** (proposal → specs → design → tasks):
+
 - **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
   - The Capabilities section is critical - each capability listed will need a spec file.
 - **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
@@ -100,6 +104,7 @@ Common artifact patterns:
 For other schemas, follow the `instruction` field from the CLI output.
 
 **Guardrails**
+
 - Create ONE artifact per invocation
 - Always read dependency artifacts before creating a new one
 - Never skip artifacts or create out of order

.agent/workflows/opsx-explore.md

@@ -9,6 +9,7 @@ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wher
 **This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
 
 **Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
+
 - A vague idea: "real-time collaboration"
 - A specific problem: "the auth system is getting unwieldy"
 - A change name: "add-dark-mode" (to explore in context of that change)
@@ -33,24 +34,28 @@ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wher
 Depending on what the user brings, you might:
 
 **Explore the problem space**
+
 - Ask clarifying questions that emerge from what they said
 - Challenge assumptions
 - Reframe the problem
 - Find analogies
 
 **Investigate the codebase**
+
 - Map existing architecture relevant to the discussion
 - Find integration points
 - Identify patterns already in use
 - Surface hidden complexity
 
 **Compare options**
+
 - Brainstorm multiple approaches
 - Build comparison tables
 - Sketch tradeoffs
 - Recommend a path (if asked)
 
 **Visualize**
+
 ```
 ┌─────────────────────────────────────────┐
 │     Use ASCII diagrams liberally        │
@@ -69,6 +74,7 @@ Depending on what the user brings, you might:
 ```
 
 **Surface risks and unknowns**
+
 - Identify what could go wrong
 - Find gaps in understanding
 - Suggest spikes or investigations
@@ -82,11 +88,13 @@ You have full context of the OpenSpec system. Use it naturally, don't force it.
 ### Check for context
 
 At the start, quickly check what exists:
+
 ```bash
 openspec list --json
 ```
 
 This tells you:
+
 - If there are active changes
 - Their names, schemas, and status
 - What the user might be working on
@@ -117,14 +125,14 @@ If the user mentions a change or you detect one is relevant:
 
 3. **Offer to capture when decisions are made**
 
-   | Insight Type | Where to Capture |
-   |--------------|------------------|
+   | Insight Type               | Where to Capture             |
+   | -------------------------- | ---------------------------- |
    | New requirement discovered | `specs/<capability>/spec.md` |
-   | Requirement changed | `specs/<capability>/spec.md` |
-   | Design decision made | `design.md` |
-   | Scope changed | `proposal.md` |
-   | New work identified | `tasks.md` |
-   | Assumption invalidated | Relevant artifact |
+   | Requirement changed        | `specs/<capability>/spec.md` |
+   | Design decision made       | `design.md`                  |
+   | Scope changed              | `proposal.md`                |
+   | New work identified        | `tasks.md`                   |
+   | Assumption invalidated     | Relevant artifact            |
 
    Example offers:
    - "That's a design decision. Capture it in design.md?"

.agent/workflows/opsx-ff.md

@@ -11,6 +11,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 1. **If no input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -18,15 +19,19 @@ Fast-forward through artifact creation - generate everything needed to start imp
    **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
 
 2. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    This creates a scaffolded change at `openspec/changes/<name>/`.
 
 3. **Get the artifact build order**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to get:
    - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
    - `artifacts`: list of all artifacts with their status and dependencies
@@ -38,30 +43,30 @@ Fast-forward through artifact creation - generate everything needed to start imp
    Loop through artifacts in dependency order (artifacts with no pending dependencies first):
 
    a. **For each artifact that is `ready` (dependencies satisfied)**:
-      - Get instructions:
-        ```bash
-        openspec instructions <artifact-id> --change "<name>" --json
-        ```
-      - The instructions JSON includes:
-        - `context`: Project background (constraints for you - do NOT include in output)
-        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
-        - `template`: The structure to use for your output file
-        - `instruction`: Schema-specific guidance for this artifact type
-        - `outputPath`: Where to write the artifact
-        - `dependencies`: Completed artifacts to read for context
-      - Read any completed dependency files for context
-      - Create the artifact file using `template` as the structure
-      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
-      - Show brief progress: "✓ Created <artifact-id>"
+   - Get instructions:
+     ```bash
+     openspec instructions <artifact-id> --change "<name>" --json
+     ```
+   - The instructions JSON includes:
+     - `context`: Project background (constraints for you - do NOT include in output)
+     - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+     - `template`: The structure to use for your output file
+     - `instruction`: Schema-specific guidance for this artifact type
+     - `outputPath`: Where to write the artifact
+     - `dependencies`: Completed artifacts to read for context
+   - Read any completed dependency files for context
+   - Create the artifact file using `template` as the structure
+   - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+   - Show brief progress: "✓ Created <artifact-id>"
 
    b. **Continue until all `applyRequires` artifacts are complete**
-      - After creating each artifact, re-run `openspec status --change "<name>" --json`
-      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
-      - Stop when all `applyRequires` artifacts are done
+   - After creating each artifact, re-run `openspec status --change "<name>" --json`
+   - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+   - Stop when all `applyRequires` artifacts are done
 
    c. **If an artifact requires user input** (unclear context):
-      - Use **AskUserQuestion tool** to clarify
-      - Then continue with creation
+   - Use **AskUserQuestion tool** to clarify
+   - Then continue with creation
 
 5. **Show final status**
    ```bash
@@ -71,6 +76,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 **Output**
 
 After completing all artifacts, summarize:
+
 - Change name and location
 - List of artifacts created with brief descriptions
 - What's ready: "All artifacts created! Ready for implementation."
@@ -84,6 +90,7 @@ After completing all artifacts, summarize:
 - Use the `template` as a starting point, filling in based on context
 
 **Guardrails**
+
 - Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
 - Always read dependency artifacts before creating a new one
 - If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum

.agent/workflows/opsx-new.md

@@ -11,6 +11,7 @@ Start a new change using the experimental artifact-driven approach.
 1. **If no input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -28,23 +29,29 @@ Start a new change using the experimental artifact-driven approach.
    **Otherwise**: Omit `--schema` to use the default.
 
 3. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    Add `--schema <name>` only if the user requested a specific workflow.
    This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
 
 4. **Show the artifact status**
+
    ```bash
    openspec status --change "<name>"
    ```
+
    This shows which artifacts need to be created and which are ready (dependencies satisfied).
 
 5. **Get instructions for the first artifact**
    The first artifact depends on the schema. Check the status output to find the first artifact with status "ready".
+
    ```bash
    openspec instructions <first-artifact-id> --change "<name>"
    ```
+
    This outputs the template and context for creating the first artifact.
 
 6. **STOP and wait for user direction**
@@ -52,6 +59,7 @@ Start a new change using the experimental artifact-driven approach.
 **Output**
 
 After completing the steps, summarize:
+
 - Change name and location
 - Schema/workflow being used and its artifact sequence
 - Current status (0/N artifacts complete)
@@ -59,6 +67,7 @@ After completing the steps, summarize:
 - Prompt: "Ready to create the first artifact? Run `/opsx:continue` or just describe what this change is about and I'll draft it."
 
 **Guardrails**
+
 - Do NOT create any artifacts yet - just show the instructions
 - Do NOT advance beyond showing the first artifact template
 - If the name is invalid (not kebab-case), ask for a valid name

.agent/workflows/opsx-onboard.md

@@ -15,6 +15,7 @@ openspec status --json 2>&1 || echo "NOT_INITIALIZED"
 ```
 
 **If not initialized:**
+
 > OpenSpec isn't set up in this project yet. Run `openspec init` first, then come back to `/opsx:onboard`.
 
 Stop here if not initialized.
@@ -59,6 +60,7 @@ Scan the codebase for small improvement opportunities. Look for:
 6. **Missing validation** - User input handlers without validation
 
 Also check recent git activity:
+
 ```bash
 git log --oneline -10 2>/dev/null || echo "No git history"
 ```
@@ -94,6 +96,7 @@ Which task interests you? (Pick a number or describe your own)
 ```
 
 **If nothing found:** Fall back to asking what the user wants to build:
+
 > I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
 
 ### Scope Guardrail
@@ -126,6 +129,7 @@ Before we create a change, let me quickly show you **explore mode**—it's how y
 ```
 
 Spend 1-2 minutes investigating the relevant code:
+
 - Read the file(s) involved
 - Draw a quick ASCII diagram if it helps
 - Note any considerations
@@ -151,6 +155,7 @@ Now let's create a change to hold our work.
 ## Phase 4: Create the Change
 
 **EXPLAIN:**
+
 ```
 ## Creating a Change
 
@@ -160,21 +165,25 @@ Let me create one for our task.
 ```
 
 **DO:** Create the change with a derived kebab-case name:
+
 ```bash
 openspec new change "<derived-name>"
 ```
 
 **SHOW:**
+
 ```
 Created: `openspec/changes/<name>/`
 
 The folder structure:
 ```
+
 openspec/changes/<name>/
-├── proposal.md    ← Why we're doing this (empty, we'll fill it)
-├── design.md      ← How we'll build it (empty)
-├── specs/         ← Detailed requirements (empty)
-└── tasks.md       ← Implementation checklist (empty)
+├── proposal.md ← Why we're doing this (empty, we'll fill it)
+├── design.md ← How we'll build it (empty)
+├── specs/ ← Detailed requirements (empty)
+└── tasks.md ← Implementation checklist (empty)
+
 ```
 
 Now let's fill in the first artifact—the proposal.
@@ -185,6 +194,7 @@ Now let's fill in the first artifact—the proposal.
 ## Phase 5: Proposal
 
 **EXPLAIN:**
+
 ```
 ## The Proposal
 
@@ -229,9 +239,11 @@ Does this capture the intent? I can adjust before we save it.
 **PAUSE** - Wait for user approval/feedback.
 
 After approval, save the proposal:
+
 ```bash
 openspec instructions proposal --change "<name>" --json
 ```
+
 Then write the content to `openspec/changes/<name>/proposal.md`.
 
 ```
@@ -245,6 +257,7 @@ Next up: specs.
 ## Phase 6: Specs
 
 **EXPLAIN:**
+
 ```
 ## Specs
 
@@ -254,6 +267,7 @@ For a small task like this, we might only need one spec file.
 ```
 
 **DO:** Create the spec file:
+
 ```bash
 mkdir -p openspec/changes/<name>/specs/<capability-name>
 ```
@@ -289,6 +303,7 @@ Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
 ## Phase 7: Design
 
 **EXPLAIN:**
+
 ```
 ## Design
 
@@ -334,6 +349,7 @@ Save to `openspec/changes/<name>/design.md`.
 ## Phase 8: Tasks
 
 **EXPLAIN:**
+
 ```
 ## Tasks
 
@@ -372,6 +388,7 @@ Save to `openspec/changes/<name>/tasks.md`.
 ## Phase 9: Apply (Implementation)
 
 **EXPLAIN:**
+
 ```
 ## Implementation
 
@@ -406,6 +423,7 @@ The change is implemented! One more step—let's archive it.
 ## Phase 10: Archive
 
 **EXPLAIN:**
+
 ```
 ## Archiving
 
@@ -415,11 +433,13 @@ Archived changes become your project's decision history—you can always find th
 ```
 
 **DO:**
+
 ```bash
 openspec archive "<name>"
 ```
 
 **SHOW:**
+
 ```
 Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
 

.agent/workflows/opsx-sync.md

@@ -40,28 +40,28 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 
    c. **Apply changes intelligently**:
 
-      **ADDED Requirements:**
-      - If requirement doesn't exist in main spec → add it
-      - If requirement already exists → update it to match (treat as implicit MODIFIED)
+   **ADDED Requirements:**
+   - If requirement doesn't exist in main spec → add it
+   - If requirement already exists → update it to match (treat as implicit MODIFIED)
 
-      **MODIFIED Requirements:**
-      - Find the requirement in main spec
-      - Apply the changes - this can be:
-        - Adding new scenarios (don't need to copy existing ones)
-        - Modifying existing scenarios
-        - Changing the requirement description
-      - Preserve scenarios/content not mentioned in the delta
+   **MODIFIED Requirements:**
+   - Find the requirement in main spec
+   - Apply the changes - this can be:
+     - Adding new scenarios (don't need to copy existing ones)
+     - Modifying existing scenarios
+     - Changing the requirement description
+   - Preserve scenarios/content not mentioned in the delta
 
-      **REMOVED Requirements:**
-      - Remove the entire requirement block from main spec
+   **REMOVED Requirements:**
+   - Remove the entire requirement block from main spec
 
-      **RENAMED Requirements:**
-      - Find the FROM requirement, rename to TO
+   **RENAMED Requirements:**
+   - Find the FROM requirement, rename to TO
 
    d. **Create new main spec** if capability doesn't exist yet:
-      - Create `openspec/specs/<capability>/spec.md`
-      - Add Purpose section (can be brief, mark as TBD)
-      - Add Requirements section with the ADDED requirements
+   - Create `openspec/specs/<capability>/spec.md`
+   - Add Purpose section (can be brief, mark as TBD)
+   - Add Requirements section with the ADDED requirements
 
 4. **Show summary**
 
@@ -75,16 +75,20 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 ## ADDED Requirements
 
 ### Requirement: New Feature
+
 The system SHALL do something new.
 
 #### Scenario: Basic case
+
 - **WHEN** user does X
 - **THEN** system does Y
 
 ## MODIFIED Requirements
 
 ### Requirement: Existing Feature
+
 #### Scenario: New scenario to add
+
 - **WHEN** user does A
 - **THEN** system does B
 
@@ -101,8 +105,9 @@ The system SHALL do something new.
 **Key Principle: Intelligent Merging**
 
 Unlike programmatic merging, you can apply **partial updates**:
+
 - To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
-- The delta represents *intent*, not a wholesale replacement
+- The delta represents _intent_, not a wholesale replacement
 - Use your judgment to merge changes sensibly
 
 **Output On Success**
@@ -124,6 +129,7 @@ Main specs are now updated. The change remains active - archive when implementat
 ```
 
 **Guardrails**
+
 - Read both delta and main specs before making changes
 - Preserve existing content not mentioned in delta
 - If something is unclear, ask for clarification

.agent/workflows/opsx-verify.md

@@ -19,9 +19,11 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
 2. **Check status to understand the schema**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand:
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifacts exist for this change
@@ -103,6 +105,7 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
 8. **Generate Verification Report**
 
    **Summary Scorecard**:
+
    ```
    ## Verification Report: <change-name>
 
@@ -115,7 +118,6 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
    ```
 
    **Issues by Priority**:
-
    1. **CRITICAL** (Must fix before archive):
       - Incomplete tasks
       - Missing requirement implementations
@@ -154,6 +156,7 @@ Verify that an implementation matches the change artifacts (specs, tasks, design
 **Output Format**
 
 Use clear markdown with:
+
 - Table for summary scorecard
 - Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
 - Code references in format: `file.ts:123`

.agents/skills/lodash-es-runtime-guards/SKILL.md

@@ -0,0 +1,74 @@
+# lodash-es-runtime-guards
+
+Replace runtime `typeof` checks and ad-hoc empty-string checks with `lodash-es` predicates.
+
+## When to Use
+
+- You see runtime checks like `typeof value === 'string'`.
+- You see object guards like `value && typeof value === 'object'`.
+- You see emptiness checks like `value.trim() !== ''` or `value.trim() === ''`.
+- You want consistent guard style across app, server, IPC, and tests.
+
+## Do Not Replace
+
+- Type-level `typeof` (TypeScript only), for example:
+  - `ReturnType<typeof fn>`
+  - `keyof typeof CONST_MAP`
+  - `z.infer<typeof Schema>`
+
+These are compile-time types and must remain as-is.
+
+## Guard Mapping
+
+- `typeof x === 'string'` -> `isString(x)`
+- `typeof x !== 'string'` -> `!isString(x)`
+- `typeof x === 'number'` -> `isNumber(x)`
+- `typeof x === 'boolean'` -> `isBoolean(x)`
+- `typeof x === 'function'` -> `isFunction(x)`
+- `typeof x === 'undefined'` -> `isUndefined(x)`
+- `x && typeof x === 'object'` -> `isObjectLike(x)`
+- `typeof x === 'object' && x !== null` -> `isObjectLike(x)`
+- `typeof x === 'object' && !Array.isArray(x)` -> `isObjectLike(x) && !isArray(x)`
+
+## String Emptiness Pattern
+
+- Prefer:
+  - `isEmpty(value.trim())`
+- Instead of:
+  - `value.trim() === ''`
+  - `value.trim() !== ''`
+  - `value.trim().length === 0`
+
+## Import Style
+
+- Use named imports from `lodash-es`:
+
+```ts
+import { isString, isNumber, isObjectLike, isEmpty } from 'lodash-es';
+```
+
+- Do not use full-package imports.
+- Reuse existing imports in file; avoid duplicate imports.
+
+## Refactor Checklist
+
+1. Replace runtime checks first, preserving behavior.
+2. Keep array/object branching semantics unchanged.
+3. Re-scan:
+
+```bash
+rg -n "typeof\s+[^\n]+(?:===|!==)\s*'" src
+```
+
+4. Confirm only type-level `typeof` remains:
+
+```bash
+rg -n "\btypeof\b" src
+```
+
+5. Run verification:
+
+```bash
+npm run type-check
+```
+

.claude/commands/opsx/apply.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Apply"
+name: 'OPSX: Apply'
 description: Implement tasks from an OpenSpec change (Experimental)
 category: Workflow
 tags: [workflow, artifacts, experimental]
@@ -21,9 +21,11 @@ Implement tasks from an OpenSpec change.
    Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
 
 2. **Check status to understand the schema**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand:
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
@@ -135,6 +137,7 @@ What would you like to do?
 ```
 
 **Guardrails**
+
 - Keep going through tasks until done or blocked
 - Always read context files before starting (from the apply instructions output)
 - If task is ambiguous, pause and ask before implementing

.claude/commands/opsx/archive.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Archive"
+name: 'OPSX: Archive'
 description: Archive a completed change in the experimental workflow
 category: Workflow
 tags: [workflow, archive, experimental]
@@ -64,6 +64,7 @@ Archive a completed change in the experimental workflow.
 5. **Perform the archive**
 
    Create the archive directory if it doesn't exist:
+
    ```bash
    mkdir -p openspec/changes/archive
    ```
@@ -148,6 +149,7 @@ Target archive directory already exists.
 ```
 
 **Guardrails**
+
 - Always prompt for change selection if not provided
 - Use artifact graph (openspec status --json) for completion checking
 - Don't block archive on warnings - just inform and confirm

.claude/commands/opsx/bulk-archive.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Bulk Archive"
+name: 'OPSX: Bulk Archive'
 description: Archive multiple completed changes at once
 category: Workflow
 tags: [workflow, archive, experimental, bulk]
@@ -33,16 +33,16 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    For each selected change, collect:
 
    a. **Artifact status** - Run `openspec status --change "<name>" --json`
-      - Parse `schemaName` and `artifacts` list
-      - Note which artifacts are `done` vs other states
+   - Parse `schemaName` and `artifacts` list
+   - Note which artifacts are `done` vs other states
 
    b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
-      - Count `- [ ]` (incomplete) vs `- [x]` (complete)
-      - If no tasks file exists, note as "No tasks"
+   - Count `- [ ]` (incomplete) vs `- [x]` (complete)
+   - If no tasks file exists, note as "No tasks"
 
    c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
-      - List which capability specs exist
-      - For each, extract requirement names (lines matching `### Requirement: <name>`)
+   - List which capability specs exist
+   - For each, extract requirement names (lines matching `### Requirement: <name>`)
 
 4. **Detect spec conflicts**
 
@@ -62,18 +62,18 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
 
    b. **Search the codebase** for implementation evidence:
-      - Look for code implementing requirements from each delta spec
-      - Check for related files, functions, or tests
+   - Look for code implementing requirements from each delta spec
+   - Check for related files, functions, or tests
 
    c. **Determine resolution**:
-      - If only one change is actually implemented -> sync that one's specs
-      - If both implemented -> apply in chronological order (older first, newer overwrites)
-      - If neither implemented -> skip spec sync, warn user
+   - If only one change is actually implemented -> sync that one's specs
+   - If both implemented -> apply in chronological order (older first, newer overwrites)
+   - If neither implemented -> skip spec sync, warn user
 
    d. **Record resolution** for each conflict:
-      - Which change's specs to apply
-      - In what order (if both)
-      - Rationale (what was found in codebase)
+   - Which change's specs to apply
+   - In what order (if both)
+   - Rationale (what was found in codebase)
 
 6. **Show consolidated status table**
 
@@ -89,12 +89,14 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    For conflicts, show the resolution:
+
    ```
    * Conflict resolution:
      - auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
    ```
 
    For incomplete changes, show warnings:
+
    ```
    Warnings:
    - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
@@ -103,7 +105,6 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 7. **Confirm batch operation**
 
    Use **AskUserQuestion tool** with a single confirmation:
-
    - "Archive N changes?" with options based on status
    - Options might include:
      - "Archive all N changes"
@@ -117,20 +118,21 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    Process changes in the determined order (respecting conflict resolution):
 
    a. **Sync specs** if delta specs exist:
-      - Use the openspec-sync-specs approach (agent-driven intelligent merge)
-      - For conflicts, apply in resolved order
-      - Track if sync was done
+   - Use the openspec-sync-specs approach (agent-driven intelligent merge)
+   - For conflicts, apply in resolved order
+   - Track if sync was done
 
    b. **Perform the archive**:
-      ```bash
-      mkdir -p openspec/changes/archive
-      mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
-      ```
+
+   ```bash
+   mkdir -p openspec/changes/archive
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
 
    c. **Track outcome** for each change:
-      - Success: archived successfully
-      - Failed: error during archive (record error)
-      - Skipped: user chose not to archive (if applicable)
+   - Success: archived successfully
+   - Failed: error during archive (record error)
+   - Skipped: user chose not to archive (if applicable)
 
 9. **Display summary**
 
@@ -153,6 +155,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    ```
 
    If any failures:
+
    ```
    Failed 1 change:
    - some-change: Archive directory already exists
@@ -161,6 +164,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 **Conflict Resolution Examples**
 
 Example 1: Only one implemented
+
 ```
 Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
 
@@ -176,6 +180,7 @@ Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
 ```
 
 Example 2: Both implemented
+
 ```
 Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
 
@@ -229,6 +234,7 @@ No active changes found. Use `/opsx:new` to create a new change.
 ```
 
 **Guardrails**
+
 - Allow any number of changes (1+ is fine, 2+ is the typical use case)
 - Always prompt for selection, never auto-select
 - Detect spec conflicts early and resolve by checking codebase

.claude/commands/opsx/continue.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Continue"
+name: 'OPSX: Continue'
 description: Continue working on a change - create the next artifact (Experimental)
 category: Workflow
 tags: [workflow, artifacts, experimental]
@@ -26,9 +26,11 @@ Continue working on a change by creating the next artifact.
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
 2. **Check current status**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to understand current state. The response includes:
    - `schemaName`: The workflow schema being used (e.g., "spec-driven")
    - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
@@ -36,7 +38,7 @@ Continue working on a change by creating the next artifact.
 
 3. **Act based on status**:
 
-   ---
+   ***
 
    **If all artifacts are complete (`isComplete: true`)**:
    - Congratulate the user
@@ -44,7 +46,7 @@ Continue working on a change by creating the next artifact.
    - Suggest: "All artifacts created! You can now implement this change with `/opsx:apply` or archive it with `/opsx:archive`."
    - STOP
 
-   ---
+   ***
 
    **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
    - Pick the FIRST artifact with `status: "ready"` from the status output
@@ -67,7 +69,7 @@ Continue working on a change by creating the next artifact.
    - Show what was created and what's now unlocked
    - STOP after creating ONE artifact
 
-   ---
+   ***
 
    **If no artifacts are ready (all blocked)**:
    - This shouldn't happen with a valid schema
@@ -81,6 +83,7 @@ Continue working on a change by creating the next artifact.
 **Output**
 
 After each invocation, show:
+
 - Which artifact was created
 - Schema workflow being used
 - Current progress (N/M complete)
@@ -94,6 +97,7 @@ The artifact types and their purpose depend on the schema. Use the `instruction`
 Common artifact patterns:
 
 **spec-driven schema** (proposal → specs → design → tasks):
+
 - **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
   - The Capabilities section is critical - each capability listed will need a spec file.
 - **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
@@ -103,6 +107,7 @@ Common artifact patterns:
 For other schemas, follow the `instruction` field from the CLI output.
 
 **Guardrails**
+
 - Create ONE artifact per invocation
 - Always read dependency artifacts before creating a new one
 - Never skip artifacts or create out of order

.claude/commands/opsx/explore.md

@@ -1,6 +1,6 @@
 ---
-name: "OPSX: Explore"
-description: "Enter explore mode - think through ideas, investigate problems, clarify requirements"
+name: 'OPSX: Explore'
+description: 'Enter explore mode - think through ideas, investigate problems, clarify requirements'
 category: Workflow
 tags: [workflow, explore, experimental, thinking]
 ---
@@ -12,6 +12,7 @@ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wher
 **This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
 
 **Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
+
 - A vague idea: "real-time collaboration"
 - A specific problem: "the auth system is getting unwieldy"
 - A change name: "add-dark-mode" (to explore in context of that change)
@@ -36,24 +37,28 @@ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wher
 Depending on what the user brings, you might:
 
 **Explore the problem space**
+
 - Ask clarifying questions that emerge from what they said
 - Challenge assumptions
 - Reframe the problem
 - Find analogies
 
 **Investigate the codebase**
+
 - Map existing architecture relevant to the discussion
 - Find integration points
 - Identify patterns already in use
 - Surface hidden complexity
 
 **Compare options**
+
 - Brainstorm multiple approaches
 - Build comparison tables
 - Sketch tradeoffs
 - Recommend a path (if asked)
 
 **Visualize**
+
 ```
 ┌─────────────────────────────────────────┐
 │     Use ASCII diagrams liberally        │
@@ -72,6 +77,7 @@ Depending on what the user brings, you might:
 ```
 
 **Surface risks and unknowns**
+
 - Identify what could go wrong
 - Find gaps in understanding
 - Suggest spikes or investigations
@@ -85,11 +91,13 @@ You have full context of the OpenSpec system. Use it naturally, don't force it.
 ### Check for context
 
 At the start, quickly check what exists:
+
 ```bash
 openspec list --json
 ```
 
 This tells you:
+
 - If there are active changes
 - Their names, schemas, and status
 - What the user might be working on
@@ -120,14 +128,14 @@ If the user mentions a change or you detect one is relevant:
 
 3. **Offer to capture when decisions are made**
 
-   | Insight Type | Where to Capture |
-   |--------------|------------------|
+   | Insight Type               | Where to Capture             |
+   | -------------------------- | ---------------------------- |
    | New requirement discovered | `specs/<capability>/spec.md` |
-   | Requirement changed | `specs/<capability>/spec.md` |
-   | Design decision made | `design.md` |
-   | Scope changed | `proposal.md` |
-   | New work identified | `tasks.md` |
-   | Assumption invalidated | Relevant artifact |
+   | Requirement changed        | `specs/<capability>/spec.md` |
+   | Design decision made       | `design.md`                  |
+   | Scope changed              | `proposal.md`                |
+   | New work identified        | `tasks.md`                   |
+   | Assumption invalidated     | Relevant artifact            |
 
    Example offers:
    - "That's a design decision. Capture it in design.md?"

.claude/commands/opsx/ff.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Fast Forward"
+name: 'OPSX: Fast Forward'
 description: Create a change and generate all artifacts needed for implementation in one go
 category: Workflow
 tags: [workflow, artifacts, experimental]
@@ -14,6 +14,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 1. **If no input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -21,15 +22,19 @@ Fast-forward through artifact creation - generate everything needed to start imp
    **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
 
 2. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    This creates a scaffolded change at `openspec/changes/<name>/`.
 
 3. **Get the artifact build order**
+
    ```bash
    openspec status --change "<name>" --json
    ```
+
    Parse the JSON to get:
    - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
    - `artifacts`: list of all artifacts with their status and dependencies
@@ -41,30 +46,30 @@ Fast-forward through artifact creation - generate everything needed to start imp
    Loop through artifacts in dependency order (artifacts with no pending dependencies first):
 
    a. **For each artifact that is `ready` (dependencies satisfied)**:
-      - Get instructions:
-        ```bash
-        openspec instructions <artifact-id> --change "<name>" --json
-        ```
-      - The instructions JSON includes:
-        - `context`: Project background (constraints for you - do NOT include in output)
-        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
-        - `template`: The structure to use for your output file
-        - `instruction`: Schema-specific guidance for this artifact type
-        - `outputPath`: Where to write the artifact
-        - `dependencies`: Completed artifacts to read for context
-      - Read any completed dependency files for context
-      - Create the artifact file using `template` as the structure
-      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
-      - Show brief progress: "✓ Created <artifact-id>"
+   - Get instructions:
+     ```bash
+     openspec instructions <artifact-id> --change "<name>" --json
+     ```
+   - The instructions JSON includes:
+     - `context`: Project background (constraints for you - do NOT include in output)
+     - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+     - `template`: The structure to use for your output file
+     - `instruction`: Schema-specific guidance for this artifact type
+     - `outputPath`: Where to write the artifact
+     - `dependencies`: Completed artifacts to read for context
+   - Read any completed dependency files for context
+   - Create the artifact file using `template` as the structure
+   - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+   - Show brief progress: "✓ Created <artifact-id>"
 
    b. **Continue until all `applyRequires` artifacts are complete**
-      - After creating each artifact, re-run `openspec status --change "<name>" --json`
-      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
-      - Stop when all `applyRequires` artifacts are done
+   - After creating each artifact, re-run `openspec status --change "<name>" --json`
+   - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+   - Stop when all `applyRequires` artifacts are done
 
    c. **If an artifact requires user input** (unclear context):
-      - Use **AskUserQuestion tool** to clarify
-      - Then continue with creation
+   - Use **AskUserQuestion tool** to clarify
+   - Then continue with creation
 
 5. **Show final status**
    ```bash
@@ -74,6 +79,7 @@ Fast-forward through artifact creation - generate everything needed to start imp
 **Output**
 
 After completing all artifacts, summarize:
+
 - Change name and location
 - List of artifacts created with brief descriptions
 - What's ready: "All artifacts created! Ready for implementation."
@@ -87,6 +93,7 @@ After completing all artifacts, summarize:
 - Use the `template` as a starting point, filling in based on context
 
 **Guardrails**
+
 - Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
 - Always read dependency artifacts before creating a new one
 - If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum

.claude/commands/opsx/new.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: New"
+name: 'OPSX: New'
 description: Start a new change using the experimental artifact workflow (OPSX)
 category: Workflow
 tags: [workflow, artifacts, experimental]
@@ -14,6 +14,7 @@ Start a new change using the experimental artifact-driven approach.
 1. **If no input provided, ask what they want to build**
 
    Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+
    > "What change do you want to work on? Describe what you want to build or fix."
 
    From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
@@ -31,23 +32,29 @@ Start a new change using the experimental artifact-driven approach.
    **Otherwise**: Omit `--schema` to use the default.
 
 3. **Create the change directory**
+
    ```bash
    openspec new change "<name>"
    ```
+
    Add `--schema <name>` only if the user requested a specific workflow.
    This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
 
 4. **Show the artifact status**
+
    ```bash
    openspec status --change "<name>"
    ```
+
    This shows which artifacts need to be created and which are ready (dependencies satisfied).
 
 5. **Get instructions for the first artifact**
    The first artifact depends on the schema. Check the status output to find the first artifact with status "ready".
+
    ```bash
    openspec instructions <first-artifact-id> --change "<name>"
    ```
+
    This outputs the template and context for creating the first artifact.
 
 6. **STOP and wait for user direction**
@@ -55,6 +62,7 @@ Start a new change using the experimental artifact-driven approach.
 **Output**
 
 After completing the steps, summarize:
+
 - Change name and location
 - Schema/workflow being used and its artifact sequence
 - Current status (0/N artifacts complete)
@@ -62,6 +70,7 @@ After completing the steps, summarize:
 - Prompt: "Ready to create the first artifact? Run `/opsx:continue` or just describe what this change is about and I'll draft it."
 
 **Guardrails**
+
 - Do NOT create any artifacts yet - just show the instructions
 - Do NOT advance beyond showing the first artifact template
 - If the name is invalid (not kebab-case), ask for a valid name

.claude/commands/opsx/onboard.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Onboard"
+name: 'OPSX: Onboard'
 description: Guided onboarding - walk through a complete OpenSpec workflow cycle with narration
 category: Workflow
 tags: [workflow, onboarding, tutorial, learning]
@@ -18,6 +18,7 @@ openspec status --json 2>&1 || echo "NOT_INITIALIZED"
 ```
 
 **If not initialized:**
+
 > OpenSpec isn't set up in this project yet. Run `openspec init` first, then come back to `/opsx:onboard`.
 
 Stop here if not initialized.
@@ -62,6 +63,7 @@ Scan the codebase for small improvement opportunities. Look for:
 6. **Missing validation** - User input handlers without validation
 
 Also check recent git activity:
+
 ```bash
 git log --oneline -10 2>/dev/null || echo "No git history"
 ```
@@ -97,6 +99,7 @@ Which task interests you? (Pick a number or describe your own)
 ```
 
 **If nothing found:** Fall back to asking what the user wants to build:
+
 > I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
 
 ### Scope Guardrail
@@ -129,6 +132,7 @@ Before we create a change, let me quickly show you **explore mode**—it's how y
 ```
 
 Spend 1-2 minutes investigating the relevant code:
+
 - Read the file(s) involved
 - Draw a quick ASCII diagram if it helps
 - Note any considerations
@@ -154,6 +158,7 @@ Now let's create a change to hold our work.
 ## Phase 4: Create the Change
 
 **EXPLAIN:**
+
 ```
 ## Creating a Change
 
@@ -163,21 +168,25 @@ Let me create one for our task.
 ```
 
 **DO:** Create the change with a derived kebab-case name:
+
 ```bash
 openspec new change "<derived-name>"
 ```
 
 **SHOW:**
+
 ```
 Created: `openspec/changes/<name>/`
 
 The folder structure:
 ```
+
 openspec/changes/<name>/
-├── proposal.md    ← Why we're doing this (empty, we'll fill it)
-├── design.md      ← How we'll build it (empty)
-├── specs/         ← Detailed requirements (empty)
-└── tasks.md       ← Implementation checklist (empty)
+├── proposal.md ← Why we're doing this (empty, we'll fill it)
+├── design.md ← How we'll build it (empty)
+├── specs/ ← Detailed requirements (empty)
+└── tasks.md ← Implementation checklist (empty)
+
 ```
 
 Now let's fill in the first artifact—the proposal.
@@ -188,6 +197,7 @@ Now let's fill in the first artifact—the proposal.
 ## Phase 5: Proposal
 
 **EXPLAIN:**
+
 ```
 ## The Proposal
 
@@ -232,9 +242,11 @@ Does this capture the intent? I can adjust before we save it.
 **PAUSE** - Wait for user approval/feedback.
 
 After approval, save the proposal:
+
 ```bash
 openspec instructions proposal --change "<name>" --json
 ```
+
 Then write the content to `openspec/changes/<name>/proposal.md`.
 
 ```
@@ -248,6 +260,7 @@ Next up: specs.
 ## Phase 6: Specs
 
 **EXPLAIN:**
+
 ```
 ## Specs
 
@@ -257,6 +270,7 @@ For a small task like this, we might only need one spec file.
 ```
 
 **DO:** Create the spec file:
+
 ```bash
 mkdir -p openspec/changes/<name>/specs/<capability-name>
 ```
@@ -292,6 +306,7 @@ Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
 ## Phase 7: Design
 
 **EXPLAIN:**
+
 ```
 ## Design
 
@@ -337,6 +352,7 @@ Save to `openspec/changes/<name>/design.md`.
 ## Phase 8: Tasks
 
 **EXPLAIN:**
+
 ```
 ## Tasks
 
@@ -375,6 +391,7 @@ Save to `openspec/changes/<name>/tasks.md`.
 ## Phase 9: Apply (Implementation)
 
 **EXPLAIN:**
+
 ```
 ## Implementation
 
@@ -409,6 +426,7 @@ The change is implemented! One more step—let's archive it.
 ## Phase 10: Archive
 
 **EXPLAIN:**
+
 ```
 ## Archiving
 
@@ -418,11 +436,13 @@ Archived changes become your project's decision history—you can always find th
 ```
 
 **DO:**
+
 ```bash
 openspec archive "<name>"
 ```
 
 **SHOW:**
+
 ```
 Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
 

.claude/commands/opsx/sync.md

@@ -1,5 +1,5 @@
 ---
-name: "OPSX: Sync"
+name: 'OPSX: Sync'
 description: Sync delta specs from a change to main specs
 category: Workflow
 tags: [workflow, specs, experimental]
@@ -43,28 +43,28 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 
    c. **Apply changes intelligently**:
 
-      **ADDED Requirements:**
-      - If requirement doesn't exist in main spec → add it
-      - If requirement already exists → update it to match (treat as implicit MODIFIED)
+   **ADDED Requirements:**
+   - If requirement doesn't exist in main spec → add it
+   - If requirement already exists → update it to match (treat as implicit MODIFIED)
 
-      **MODIFIED Requirements:**
-      - Find the requirement in main spec
-      - Apply the changes - this can be:
-        - Adding new scenarios (don't need to copy existing ones)
-        - Modifying existing scenarios
-        - Changing the requirement description
-      - Preserve scenarios/content not mentioned in the delta
+   **MODIFIED Requirements:**
+   - Find the requirement in main spec
+   - Apply the changes - this can be:
+     - Adding new scenarios (don't need to copy existing ones)
+     - Modifying existing scenarios
+     - Changing the requirement description
+   - Preserve scenarios/content not mentioned in the delta
 
-      **REMOVED Requirements:**
-      - Remove the entire requirement block from main spec
+   **REMOVED Requirements:**
+   - Remove the entire requirement block from main spec
 
-      **RENAMED Requirements:**
-      - Find the FROM requirement, rename to TO
+   **RENAMED Requirements:**
+   - Find the FROM requirement, rename to TO
 
    d. **Create new main spec** if capability doesn't exist yet:
-      - Create `openspec/specs/<capability>/spec.md`
-      - Add Purpose section (can be brief, mark as TBD)
-      - Add Requirements section with the ADDED requirements
+   - Create `openspec/specs/<capability>/spec.md`
+   - Add Purpose section (can be brief, mark as TBD)
+   - Add Requirements section with the ADDED requirements
 
 4. **Show summary**
 
@@ -78,16 +78,20 @@ This is an **agent-driven** operation - you will read delta specs and directly e
 ## ADDED Requirements
 
 ### Requirement: New Feature
+
 The system SHALL do something new.
 
 #### Scenario: Basic case
+
 - **WHEN** user does X
 - **THEN** system does Y
 
 ## MODIFIED Requirements
 
 ### Requirement: Existing Feature
+
 #### Scenario: New scenario to add
+
 - **WHEN** user does A
 - **THEN** system does B
 
@@ -104,8 +108,9 @@ The system SHALL do something new.
 **Key Principle: Intelligent Merging**
 
 Unlike programmatic merging, you can apply **partial updates**:
+
 - To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
-- The delta represents *intent*, not a wholesale replacement
+- The delta represents _intent_, not a wholesale replacement
 - Use your judgment to merge changes sensibly
 
 **Output On Success**
@@ -127,6 +132,7 @@ Main specs are now updated. The change remains active - archive when implementat
 ```
 
 **Guardrails**
+
 - Read both delta and main specs before making changes
 - Preserve existing content not mentioned in delta
 - If something is unclear, ask for clarification