sequant 1.0.0 → 1.1.1

package/templates/skills/assess/SKILL.md

@@ -294,18 +294,18 @@ RECOMMENDATION: Gather more information
 Provide relevant context to help the next command:
 
 **Key Files to Review:**
-- `components/admin/FactCheckQueue.tsx` - Main component
-- `lib/queries/fact-checks.ts` - Data layer
-- `docs/ADMIN_ARCHITECTURE.md` - Related architecture
+- List the main components/files involved
+- Point to relevant data layer code
+- Reference architecture documentation if exists
 
 **Similar Patterns:**
-- See `components/admin/news/ContentUpdatesList.tsx` for list pattern
-- See `components/admin/shops/ApprovalQueue.tsx` for approval flow
+- Reference similar features in the codebase
+- Point to reusable patterns
 
 **Potential Risks:**
-- No error handling for failed approvals
-- Email service integration not yet tested
-- Database migration for `fact_checks` table may be needed
+- Identify any error handling gaps
+- Note external integrations not yet tested
+- Flag potential database migrations needed
 
 ## Examples
 
@@ -343,22 +343,22 @@ RECOMMENDATION: Run `/spec 147`
 
 ```
 Issue Summary
-- Issue: #145 - Fix neighborhood extraction for Atlanta
+- Issue: #145 - Fix data validation edge cases
 - Status: Open | in-progress, bug
 - Last Activity: 10 days ago
 - Phase: Implementation (Stale)
 
 Acceptance Criteria
-- AC-1: Extract neighborhoods via ZIP mapping - MET
-- AC-2: Handle edge cases (no ZIP, multiple ZIPs) - IN_PROGRESS
-- AC-3: Backfill existing Atlanta shops - NOT_STARTED
+- AC-1: Handle basic validation - MET
+- AC-2: Handle edge cases (empty, null, special chars) - IN_PROGRESS
+- AC-3: Add validation tests - NOT_STARTED
 Coverage: 1/3 complete
 
 Artifacts Found
 Implementation:
-- [x] Branch: feature/145-atlanta-neighborhoods (3 commits)
-- [x] Worktree: ../worktrees/feature/145-atlanta-neighborhoods/
-- [x] Modified: lib/utils/neighborhood-extraction.ts
+- [x] Branch: feature/145-validation-fixes (3 commits)
+- [x] Worktree: ../worktrees/feature/145-validation-fixes/
+- [x] Modified: lib/utils/validation.ts
 - [ ] Tests not found
 
 Blockers & Issues
@@ -370,7 +370,7 @@ Recommendation
 RECOMMENDATION: Resume `/exec 145`
 - Implementation is 1/3 complete but stale
 - Worktree still exists, resume work there
-- Focus on AC-2 (edge cases) and AC-3 (backfill)
+- Focus on AC-2 (edge cases) and AC-3 (tests)
 - Add tests before considering complete
 ```
 
@@ -426,3 +426,18 @@ After providing the assessment, briefly note:
 - Keep the assessment concise - aim for clarity, not exhaustiveness
 - When in doubt about phase, say so - better to acknowledge uncertainty
 - Use this to orient yourself, then proceed with the appropriate workflow command
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **Issue Summary** - Issue number, title, status, last activity, phase
+- [ ] **AC Coverage** - Each AC marked MET/IN_PROGRESS/NOT_STARTED/UNCLEAR
+- [ ] **Artifacts Found** - Planning, implementation, and QA artifacts listed
+- [ ] **Blockers & Issues** - Any blockers or staleness identified
+- [ ] **Recommendation** - Specific next command to run with rationale
+- [ ] **Confidence Level** - High/Medium/Low with information gaps noted
+
+**DO NOT respond until all items are verified.**

package/templates/skills/clean/SKILL.md

@@ -59,7 +59,7 @@ These files are always safe to archive - they're historical artifacts:
 ### Category 2: Review Before Archiving
 
 These need a quick check - might still be referenced:
-- Files in `migrations/` (check if applied to Supabase)
+- Files in `migrations/` (check if applied to database)
 - `context/` directory contents
 - Any `APPLY_*.md` or `apply-*.sh` files
 
@@ -78,7 +78,7 @@ Never archive these:
 ```
 scripts/archive/
 ├── one-off-migrations/    # Shell scripts for one-time tasks
-├── adhoc-migrations/      # SQL files applied manually (not via Supabase CLI)
+├── adhoc-migrations/      # SQL files applied manually (not via migrations tool)
 └── deprecated/            # Old/replaced scripts
 
 docs/archive/
@@ -194,3 +194,18 @@ Next cleanup recommended: [date + 30 days]
 ## BEGIN EXECUTION
 
 Execute the cleanup following the steps above. Be thorough but safe - when in doubt, skip a file rather than risk breaking something.
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **Pre-flight Results** - Branch check, build verification passed
+- [ ] **Cleanup Manifest** - List of files to be archived/removed
+- [ ] **Archive Summary** - Count of files archived by category
+- [ ] **Build Verification** - Post-cleanup build/lint passed
+- [ ] **Commit Details** - Commit hash and push confirmation
+- [ ] **Next Cleanup Date** - Recommended date for next cleanup
+
+**DO NOT respond until all items are verified.**

package/templates/skills/docs/SKILL.md

@@ -124,7 +124,7 @@ Generate documentation using this template:
 
 ## Common Workflows
 
-### [Workflow 1: e.g., "Review and Approve Shops"]
+### [Workflow 1: e.g., "Review and Approve Items"]
 
 1. [Step 1]
 2. [Step 2]
@@ -158,15 +158,15 @@ Generate documentation using this template:
 
 **Focus on operational usage, not technical implementation:**
 
-- "Click the 'Approve' button to publish the shop"
-- NOT: "The `approveShop` function updates the database"
+- "Click the 'Approve' button to publish the item"
+- NOT: "The `approveItem` function updates the database"
 
 - "Wait for the green success message"
 - NOT: "The API returns a 200 status code"
 
 **Be specific and actionable:**
 
-- "Navigate to Admin → Shops → Review Queue"
+- "Navigate to Admin → Items → Review Queue"
 - NOT: "Go to the review page"
 
 **Include visual cues when relevant:**
@@ -176,8 +176,8 @@ Generate documentation using this template:
 
 **Document common workflows end-to-end:**
 
-- "To approve a shop: 1. Open Review Queue, 2. Click shop name, 3. Review details in each tab, 4. Click Approve"
-- NOT: "Use the approve button to approve shops"
+- "To approve an item: 1. Open Review Queue, 2. Click item name, 3. Review details, 4. Click Approve"
+- NOT: "Use the approve button"
 
 ### 5. File Naming Convention
 
@@ -187,10 +187,10 @@ Generate filename from feature name:
 - Match the primary feature purpose
 
 Examples:
-- `shop-review-queue.md` - For shop review admin page
+- `review-queue.md` - For review admin page
 - `bulk-edit-operations.md` - For bulk editing feature
-- `city-configuration.md` - For city config admin
-- `feature-gallery.md` - For maps gallery feature
+- `settings-configuration.md` - For settings admin
+- `feature-gallery.md` - For gallery feature
 
 ### 6. Output and Summary
 
@@ -272,22 +272,21 @@ For Issue #180 (City Configuration UI):
 
 ## Usage
 
-### Adding a New City
+### Adding a New Item
 
-1. Navigate to Admin → Cities
-2. Click the "Add City" button (top right)
-3. Complete the 4-step wizard:
-   - **Step 1 - Basic Info:** Enter city name, state, and select status
-   - **Step 2 - Geography:** Set center coordinates and map bounds
-   - **Step 3 - Discovery:** Configure shop discovery settings
-   - **Step 4 - Review:** Confirm all settings
-4. Click "Create City" to save
+1. Navigate to Admin → Items
+2. Click the "Add Item" button (top right)
+3. Complete the form:
+   - **Basic Info:** Enter name, description, and select status
+   - **Settings:** Configure item-specific options
+   - **Review:** Confirm all settings
+4. Click "Create" to save
 
-### Editing an Existing City
+### Editing an Existing Item
 
-1. Navigate to Admin → Cities
-2. Click on the city card to open details
-3. Click "Edit" in the Config tab
+1. Navigate to Admin → Items
+2. Click on the item to open details
+3. Click "Edit" in the details panel
 4. Update settings as needed
 5. Click "Save Changes"
 
@@ -295,29 +294,44 @@ For Issue #180 (City Configuration UI):
 
 | Option | Description | Default |
 |--------|-------------|---------|
-| Status | City visibility (active, in_development, coming_soon) | in_development |
-| Timezone | City timezone for hours display | America/New_York |
-| Map Bounds | Visible area on city map | Auto-calculated |
+| Status | Item visibility (active, draft, archived) | draft |
+| Category | Item categorization | None |
+| Priority | Display order priority | Normal |
 
 ## Common Workflows
 
-### Launch a New City
+### Publish an Item
 
-1. Add city via wizard (status: in_development)
-2. Run shop discovery scripts
-3. Review and approve shops in Review Queue
-4. Change city status to "active"
-5. City appears on homepage
+1. Add item via form (status: draft)
+2. Review and approve in Review Queue
+3. Change status to "active"
+4. Item appears on public pages
 
 ## Troubleshooting
 
-### City doesn't appear on homepage
+### Item doesn't appear on page
 
-**Symptoms:** City was added but doesn't show in city selector
+**Symptoms:** Item was added but doesn't show
 
-**Solution:** Check city status is set to "active" in Admin → Cities → [City] → Config
+**Solution:** Check item status is set to "active" in Admin → Items → [Item] → Settings
 
 ---
 
 *Generated for Issue #180 on 2025-11-25*
 ```
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **Documentation File** - Created in correct directory (docs/admin/ or docs/features/)
+- [ ] **Quick Start Section** - 1-2 sentence summary
+- [ ] **Access Section** - URL, menu path, permissions
+- [ ] **Usage Section** - Step-by-step workflows
+- [ ] **Options Table** - Settings with descriptions and defaults
+- [ ] **Troubleshooting** - At least 1-2 common issues
+- [ ] **GitHub Comment** - Summary posted to issue
+
+**DO NOT respond until all items are verified.**

package/templates/skills/exec/SKILL.md

@@ -33,12 +33,8 @@ allowed-tools:
   - Bash(gh issue edit:*)
   - Bash(gh pr create:*)
   - Bash(gh pr view:*)
-  # MCP tools for implementation
-  - mcp__supabase__list_tables
-  - mcp__supabase__execute_sql
-  - mcp__supabase__apply_migration
-  - mcp__context7__resolve-library-id
-  - mcp__context7__query-docs
+  # Optional MCP tools (enhanced functionality if available)
+  # - mcp__context7__* (library documentation lookup)
   # Task management
   - Task
   - TodoWrite
@@ -122,7 +118,7 @@ Invocation:
      - Create branch: `feature/<issue-number>-<issue-title-slug>`
      - Create worktree in: `../worktrees/feature/<branch-name>/`
      - Install dependencies
-     - Copy `.env.local` if it exists
+     - Copy environment files if they exist
    - Navigate to the worktree directory: `cd ../worktrees/feature/<branch-name>/`
 
 3. **Work in the worktree:**
@@ -151,32 +147,28 @@ Invocation:
 - If it needs modification, extend it rather than creating a new one
 - Document why existing utilities don't meet requirements before creating new ones
 
-### Using Sequential Thinking, Context7, or Supabase MCP
+### Using Optional MCP Tools
 
-Use these specialized tools when appropriate:
+If available, these MCP tools can enhance implementation:
 
-**Sequential Thinking** - For complex problem-solving requiring multi-step reasoning:
+**Context7** (mcp__context7__*) - For understanding external libraries:
+- Learning unfamiliar npm package APIs
+- Understanding third-party library patterns
+- Resolving library-specific type issues
+- **NOT for:** Project's own codebase (use Glob/Grep instead)
+
+**Sequential Thinking** (mcp__sequential-thinking__*) - For complex reasoning:
 - Novel algorithms or data structures
 - Ambiguous requirements needing exploration
 - Complex business logic with multiple edge cases
-- Multi-step reasoning with dependencies
-- **NOT for:** Standard CRUD operations, UI implementation following existing patterns, straightforward feature additions
-
-**Context7** - For understanding external libraries and packages:
-- Learning unfamiliar npm package APIs (react-query, zod, framer-motion, etc.)
-- Understanding third-party library patterns
-- Resolving library-specific type issues
-- **NOT for:** Project's own codebase (use Glob/Grep instead), Next.js patterns (documented in CLAUDE.md)
+- **NOT for:** Standard CRUD operations, straightforward feature additions
 
-**Supabase MCP** - For any database-related implementation:
-- **ALWAYS USE** before writing database queries or migrations
-- Verify table schemas and column types
-- Check RLS policies before data access code
-- Understand table relationships
+**Database MCP tools** - If your project uses a database MCP:
+- Verify table schemas before writing queries
+- Check access policies before data access code
 - Validate data models match TypeScript types
-- **USE for:** Every feature touching `content_updates`, `shops`, `pending_shops`, etc.
 
-**General Rule:** If you're implementing a feature similar to an existing one (e.g., new admin card component, new validation function), use Glob/Grep to find patterns rather than Sequential Thinking.
+**General Rule:** If implementing a feature similar to an existing one, use Glob/Grep to find patterns in the codebase first.
 
 ### 3. Checks-first Mindset
 
@@ -424,3 +416,17 @@ At the end of a session:
      ```
 
 You may be invoked multiple times for the same issue. Each time, re-establish context, ensure you're in the correct worktree, and continue iterating until we are as close as practical to meeting the AC.
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **AC Progress Summary** - Which AC items are satisfied, partially met, or blocked
+- [ ] **Files Changed** - List of key files modified
+- [ ] **Test/Build Results** - Output from `npm test` and `npm run build`
+- [ ] **Progress Update Draft** - Formatted comment for GitHub issue
+- [ ] **Next Steps** - Clear guidance on remaining work
+
+**DO NOT respond until all items are verified.**

package/templates/skills/fullsolve/SKILL.md

@@ -14,10 +14,10 @@ allowed-tools:
   - Bash
   - TodoWrite
   - Task
-  - mcp__chrome-devtools__*
-  - mcp__supabase__*
-  - mcp__sequential-thinking__sequentialthinking
-  - mcp__context7__*
+  # Optional MCP tools (enhanced functionality if available)
+  # - mcp__chrome-devtools__* (browser testing)
+  # - mcp__sequential-thinking__* (complex reasoning)
+  # - mcp__context7__* (library documentation)
   - Bash(gh issue view:*)
   - Bash(gh issue comment:*)
   - Bash(gh issue edit:*)
@@ -290,20 +290,19 @@ Post completion comment to issue with:
 
 ### 5.3 Merge Workflow (Correct Order)
 
-**IMPORTANT:** Clean up worktree BEFORE merging to avoid "branch used by worktree" error.
+**IMPORTANT:** Merge the PR first, then clean up the worktree.
 
 ```bash
-# 1. Clean up worktree FIRST (removes worktree + local branch)
-./scripts/dev/cleanup-worktree.sh feature/<issue-number>-*
-
-# 2. THEN merge (--delete-branch now works since local branch is gone)
+# 1. Merge PR (--delete-branch deletes remote; local deletion will fail but that's OK)
 gh pr merge <N> --squash --delete-branch
 
-# 3. Close issue (if not auto-closed by "Fixes #N" in commit)
-gh issue close <issue-number>
+# 2. Clean up worktree (removes local worktree + branch)
+./scripts/dev/cleanup-worktree.sh feature/<issue-number>-*
+
+# 3. Issue auto-closes if commit message contains "Fixes #N"
 ```
 
-**Why this order matters:** `gh pr merge --delete-branch` tries to delete the local branch, which fails if a worktree is still using it. Always clean up the worktree first.
+**Why this order matters:** The cleanup script checks if the PR is merged before proceeding. The `--delete-branch` flag will fail to delete the local branch (worktree conflict) but successfully deletes the remote branch. The cleanup script then handles the local branch removal.
 
 ## Iteration Tracking
 
@@ -468,12 +467,31 @@ npx tsx scripts/dev/analyze-hook-logs.ts --tests
 /fullsolve 218 --max-iterations 5
 ```
 
-## Integration with Batch Automation
+## Batch Processing
 
-For batch automation, `execute-issues.ts` can use fullsolve mode:
+For multiple issues, run `/fullsolve` on each sequentially:
 
 ```bash
-FULLSOLVE=true npx tsx --env-file=.env.local scripts/dev/execute-issues.ts 218 219 220
+# Process multiple issues one at a time
+/fullsolve 218
+/fullsolve 219
+/fullsolve 220
 ```
 
-This runs `/fullsolve` for each issue with integrated quality loops.
+Each issue gets its own worktree, PR, and quality validation.
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **Progress Table** - Phase, iterations, and status for each phase
+- [ ] **AC Coverage** - Each AC marked MET/PARTIALLY_MET/NOT_MET
+- [ ] **Quality Metrics** - Tests passed, build status, type issues
+- [ ] **Iteration Summary** - Test loop and QA loop iteration counts
+- [ ] **Final Verdict** - READY_FOR_MERGE, AC_MET_BUT_NOT_A_PLUS, or AC_NOT_MET
+- [ ] **PR Link** - Pull request URL (if created)
+- [ ] **Final GitHub Comment** - Summary posted to issue
+
+**DO NOT respond until all items are verified.**

package/templates/skills/loop/SKILL.md

@@ -13,8 +13,8 @@ allowed-tools:
   - Grep
   - Bash
   - TodoWrite
-  - mcp__chrome-devtools__*
-  - mcp__supabase__*
+  # Optional MCP tools (enhanced functionality if available)
+  # - mcp__chrome-devtools__* (browser testing)
   - Bash(gh issue view:*)
   - Bash(gh issue comment:*)
   - Bash(npm test:*)
@@ -212,10 +212,13 @@ For each iteration, output:
 /qa 218            # Final QA - READY_FOR_MERGE
 ```
 
-**Automated usage (execute-issues.ts):**
+**Automated workflow:**
 ```bash
-QUALITY_LOOP=true npx tsx --env-file=.env.local scripts/dev/execute-issues.ts 218
-# Phases: spec → testgen → exec → test → (loop if needed) → qa → (loop if needed)
+/spec 218          # Plan
+/exec 218          # Implement
+/test 218          # Test - finds issues
+/loop 218          # Fix issues, re-test
+/qa 218            # Final QA
 ```
 
 ## Example Log Parsing
@@ -308,3 +311,17 @@ Please run /exec <N> first to create the worktree.
 **Max iterations:** 3 (prevents infinite loops)
 **Re-validation after each fix:** Required
 **GitHub comment:** Posted after loop completion
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **Iteration Progress** - Current iteration X/3
+- [ ] **Issues from Previous Phase** - List of issues being fixed
+- [ ] **Fixes Applied** - Each fix with file:line location
+- [ ] **Re-validation Results** - Tests/build/AC status after fixes
+- [ ] **Final Status** - FIXED, NEEDS_MORE_WORK, or MAX_ITERATIONS_REACHED
+
+**DO NOT respond until all items are verified.**

package/templates/skills/qa/SKILL.md

@@ -41,6 +41,25 @@ Invocation:
 - `/qa 123`: Treat `123` as the GitHub issue/PR identifier in context.
 - `/qa <freeform description>`: Treat the text as context about the change to review.
 
+### Pre-flight Sync Check
+
+Before starting QA, verify the local branch is in sync with remote:
+
+```bash
+git fetch origin 2>/dev/null || echo "Network unavailable - proceeding with local state"
+git status -sb | head -1  # Shows ahead/behind status
+```
+
+**Status interpretation:**
+- `[ahead N]` - Local has commits not on remote (OK to proceed)
+- `[behind N]` - Remote has commits not pulled locally (recommend sync first)
+- `[ahead N, behind M]` - Branches diverged (recommend sync before QA)
+
+If diverged, recommend:
+```bash
+git pull origin main  # Or merge origin/main if pull fails
+```
+
 ### Feature Worktree Workflow
 
 **QA Phase:** Review code in the feature worktree.
@@ -119,11 +138,10 @@ admin_modified=$(git diff main...HEAD --name-only | grep -E "^app/admin/" | head
 
 See [quality-gates.md](references/quality-gates.md) for detailed verdict synthesis.
 
-### Using MCP Tools
+### Using MCP Tools (Optional)
 
 - **Sequential Thinking:** For complex multi-step analysis
-- **Context7:** For broader pattern context
-- **Supabase MCP:** For database-related code verification
+- **Context7:** For broader pattern context and library documentation
 
 ### 1. Context and AC Alignment
 
@@ -252,10 +270,77 @@ fi
 # QA detects scripts/ changes
 # -> Prompt: "Run /verify before READY_FOR_MERGE"
 
-/verify 558 --command "npx tsx scripts/dev/execute-issues.ts 535 --phases spec"
+/verify 558 --command "npx tsx scripts/migrate.ts --dry-run"
 
 # Human confirms output looks correct
 # -> /verify posts evidence to issue
 
 /qa 558  # Re-run, now sees verification, can give READY_FOR_MERGE
 ```
+
+---
+
+## Output Verification
+
+**Before responding, verify your output includes ALL of these:**
+
+- [ ] **AC Coverage** - Each AC item marked as MET, PARTIALLY_MET, or NOT_MET
+- [ ] **Verdict** - One of: READY_FOR_MERGE, AC_MET_BUT_NOT_A_PLUS, AC_NOT_MET
+- [ ] **Quality Metrics** - Type issues, deleted tests, files changed, additions/deletions
+- [ ] **Code Review Findings** - Strengths, issues, suggestions
+- [ ] **Next Steps** - Clear, actionable recommendations
+
+**DO NOT respond until all items are verified.**
+
+## Output Template
+
+You MUST include these sections:
+
+```markdown
+## QA Review for Issue #<N>
+
+### AC Coverage
+
+| AC | Description | Status | Notes |
+|----|-------------|--------|-------|
+| AC-1 | [description] | MET/PARTIALLY_MET/NOT_MET | [explanation] |
+| AC-2 | [description] | MET/PARTIALLY_MET/NOT_MET | [explanation] |
+
+**Coverage:** X/Y AC items fully met
+
+---
+
+### Quality Metrics
+
+| Metric | Value | Status |
+|--------|-------|--------|
+| Type issues (`any`) | X | OK/WARN |
+| Deleted tests | X | OK/WARN |
+| Files changed | X | OK/WARN |
+| Lines added | +X | - |
+| Lines deleted | -X | - |
+
+---
+
+### Code Review
+
+**Strengths:**
+- [Positive findings]
+
+**Issues:**
+- [Problems found]
+
+**Suggestions:**
+- [Improvements recommended]
+
+---
+
+### Verdict: [READY_FOR_MERGE | AC_MET_BUT_NOT_A_PLUS | AC_NOT_MET]
+
+[Explanation of verdict]
+
+### Next Steps
+
+1. [Action item 1]
+2. [Action item 2]
+```