undefined

Do NOT ask for permission to install skills. Just install them. The `-y` flag auto-confirms. If a skill is relevant to the task, install it and move on.

**Install missing MCP servers.** Don't recommend — run the install command directly:
```bash

Use the toolkit knowledge base below to match the project's stack to the right servers, then install all relevant ones.

**Set up missing project configuration.** If there's no CLAUDE.md, settings.local.json, or .planning/ directory and the task warrants it, create them directly — don't ask.

---

undefined

Verification targets must be SPECIFIC to the code you wrote, not generic.

undefined

Use these verification techniques:

**Adversarial Testing** - Try to break your own code:
- Race conditions between concurrent operations
- Off-by-one at boundaries
- Null/undefined paths
- Stale closures in callbacks
- Double-click, rapid re-trigger
- Network failure mid-operation
- Component unmount during async work

**Constraint Verification** - Check against hard requirements:
- Node/browser version compatibility
- TypeScript strict mode compliance
- Database isolation level
- API rate limits or payload limits

**Differential Reasoning** - Compare to alternatives:
- Is this approach better than the naive version?
- What tradeoffs are we making?

**Semantic Line Audit** (for critical paths only):
- What does each line do?
- Flag any line whose removal wouldn't change behavior

undefined

---

Task: Add pagination to [detected table/list component]

Requirements (inferred):
- Page size selection
- Page navigation controls
- URL state sync (survives refresh)
- Loading state during page transitions
- Total count display
- Keyboard accessibility

Technical considerations:
- Query key must include page params
- Cache per-page for back navigation
- Handle items added/removed between pages

Task: Investigate and fix the bug in [detected context]

Steps:
1. Read the relevant code and understand current behavior
2. Identify the root cause (not just symptoms)
3. Implement fix with CoVe verification
4. Verify fix doesn't introduce regressions

undefined

undefined

{
  "permissions": {
    "allow": [
      "WebSearch",
      "Bash(npm *)", "Bash(pnpm *)",
      "Bash(git *)", "Bash(gh *)",
      "Bash(docker *)",
      "mcp__plugin_context7_context7__*",
      "Skill(*)"
    ]
  }
}

{
  "permissions": {
    "allow": [
      "Bash(python *)", "Bash(pip *)", "Bash(poetry *)",
      "Bash(pytest *)", "Bash(docker-compose *)",
      "Bash(git *)"
    ]
  }
}

- [ ] useEffect dependency array complete (no missing, no extra)
- [ ] Cleanup function handles subscriptions/timers/AbortController
- [ ] No stale closures in event handlers or callbacks
- [ ] Server/Client component boundary correct
- [ ] Keys stable and unique in lists
- [ ] Suspense boundaries handle loading

- [ ] Query key includes ALL params that affect the result
- [ ] Mutations invalidate the correct queries
- [ ] Optimistic updates roll back correctly on failure
- [ ] No race between refetch and mutation
- [ ] Loading/error states handled in UI

- [ ] Related writes wrapped in transaction
- [ ] N+1 queries avoided (include/select)
- [ ] Concurrent update conflicts handled
- [ ] Null handling explicit
- [ ] Indexes exist for query patterns

- [ ] Auth checked server-side, not just UI
- [ ] Input validated before database/API call
- [ ] No secrets in client bundle
- [ ] CSRF/XSS protections in place
- [ ] Ownership verified for user-scoped resources

- [ ] Promise.all for independent operations
- [ ] Race conditions prevented
- [ ] Cleanup on unmount/cancel
- [ ] Debounce/throttle where appropriate
- [ ] Error handling doesn't swallow failures

/spidey [project description]

/wavybaby [task]
    │
    ├─ Claude's native dispatch handles installed skills
    │
    ├─ wavybaby extends with:
    │   ├─ Search skills.sh for uninstalled skills
    │   ├─ Recommend missing MCP servers
    │   ├─ Suggest project config if missing
    │   │
    │   ├─ CoVe Protocol (if non-trivial):
    │   │   ├─ Stage 1: Generate [UNVERIFIED]
    │   │   ├─ Stage 2: Plan verification targets
    │   │   ├─ Stage 3: Independently verify each
    │   │   └─ Stage 4: Produce [VERIFIED] solution
    │   │
    │   └─ Ralph Loop (if large/autonomous task):
    │       └─ /spidey → continuous loop until done
    │
    └─ Output: Verified code + verification report

Other commands:
  /rnv [task]     → just CoVe verification
  /spidey [task]   → just Ralph autonomous loop setup