Read [[principles/fix-root-causes]] before starting. Every debugging session follows that principle: trace to root cause, never paper over symptoms.

Implementation methodology for executing tasks. Handles scoping, decomposition, worktree workflow, verification, and commit conventions. Triggers: "execute", "implement", "build this", "code this".

| Pattern | When to apply | |---------|---------------| | Minimal main | New binaries | | Single bootstrap | App wiring across modes | | Ordered shutdown | Long-running processes | | Non-blocking fanout | Channel-based event systems | | Concurrency testing | Any goroutine code | | Layered config | M

Skills that run themselves. Write skills with a `schedule:` field describing when they should run. Noodle's scheduler agent reads those descriptions, writes orders, and the loop spawns agents in isolated worktrees to do the work.

Infrastructure fix for broken builds, failed tests, stale state, and environment drift. Covers both user-project and Noodle-internal failures. Triggers when builds break, tests fail, state is stale, or environment drifts. Use on 'oops', 'fix the build', 'tests are failing', 'something broke', 'broken build'.

**Routing:** claude / claude-opus-4-6

TypeScript type safety guidelines for writing maximally type-safe code. Apply these patterns when writing or reviewing any TypeScript: discriminated unions, type narrowing, type guards, exhaustiveness checks, avoiding `as` casts, preferring `unknown` over `any`, and making impossible states unrepresentable. Use this skill whenever writing TypeScript code, reviewing TypeScript for type safety issues, or when the user mentions type safety, type narrowing, discriminated unions, or asks to make types stricter/more explicit.

Remove AI writing patterns from prose. Use for docs, READMEs, blog posts, any non-code text that should sound human. Triggers: "unslop", "humanize", "make this sound human", "clean up this writing", "edit for voice", "de-AI this text".

Use for concurrent sessions, agent team isolation, or any work needing a separate branch. Critical for multi-agent workflows. Triggers: "worktree", "new worktree", "clean up worktrees", "need isolation", or when spawning agent teams.