Software Development Skills

Use when fixing bugs, debugging failures, or proactively reviewing code for hidden bugs. Reactive mode: fix known bugs. Proactive mode: hunt for bugs in code. Enforces confirmed root cause before any fix.

Terminal pocket stage. User invokes after pocket-review writes verdicts. Reconciles reviews against log.json, gates on REVIEWFAIL/REVIEWBLOCKED, advances REVIEW→DONE, runs log close, and emits a closeout summary. Trigger on "pocket-closing", "close the plan", "close out", "finalize plan", or when a plan is fully reviewed and all verdicts pass.

Use when executing multi-task implementation plans. Trigger on execute plan, delegate tasks, dispatch subagents. Combines delegate handoff discipline with prompt-engineering attention mechanics.

BDD-driven feature/fix discovery before any implementation. Use when planning a feature, designing a fix, or exploring options before building. Trigger on "pocket-grinding", "brainstorm", "think through", "plan this", "before we build". Invokes pocket-planning at handoff.

Onboarding and routing guide for the Pocket skill ecosystem. Use when someone asks what Pocket is, which Pocket skill to use, how the end-to-end flow works, or when Pocket is better than lighter Superpowers-style flows. Trigger on "what is pocket", "how do I use pocket", "which pocket skill", "explain pocket", "pocket-help", or any onboarding/routing question. This is a compact entry point — it summarizes every skill so agents and users do NOT have to load each SKILL.md to orient.

Pre-grinding problem exploration. Use BEFORE pocket-grinding when the problem is unformed or needs exploration. Guides diverge→converge with structured brainstorming methods and LLM-to-LLM curation (advisor tool), then produces a pitch exploration doc. Trigger on "pocket-pitching", "pitch this", "explore this idea", "I have a rough idea", or when no clear problem definition exists yet. Do NOT use for "brainstorm" — that triggers pocket-grinding.

Converts a pocket-grinding spec into a TDD-structured execution plan of full Pocket Packets. Use when pocket-grinding handoff arrives (spec path + acceptance criteria). Trigger on "create plan", "build plan", "pocket-planning", or when pocket-grinding skill invokes this. Outputs tasks ready to dispatch via pocket-development skill.

Post-phase batch reviewer. User invokes after pocket-development marks all phase tasks DONE. Main agent runs preflight and dispatches parallel reviewer subagents (one per task). Returns PHASEREVIEWED or PHASEBLOCKED; on an all-REVIEWPASS phase it chains to pocket-closing after one confirmation.

Bridges pocket-planning and pocket-development for all execution plans. Use when pocket-planning hands off any execution plan. Routes ≤6-task plans as a passthrough to pocket-development; splits ≥7-task plans into phase files. Trigger on "structure plan", "split plan", or when pocket-planning invokes this.

Standalone skill for validating an explicit assumption with structured research. Use when a user holds a belief that is still an assumption — a technical claim, a library's behavior, a "this is probably how X works" — and wants it investigated methodically before it leaks into planning or code. Recommends a research methodology (non-binding) and returns an evidence-backed, graded verdict (Confirmed / Refuted / Inconclusive). Trigger on "structured-research", "validate this assumption", "is it true that", "research whether", "verify my assumption", "check this claim", "I assume X — is that right?". Standalone like bug-hunting / hotfix / brand-design — no pipeline required.