Claude Skills by Langerrr

This skill should be used when implementing or designing code with async data flows — "state management design", "async data flow", "stale data", "cache invalidation", "optimistic update", "init order", "race condition", "write then read", "data not updating", "cache not refreshing", "UI shows old data after save", "value doesn't update", "empty data on first load". Also applicable when working with caching layers, event-driven systems, or any code where write and read paths have different la...

This skill should be used when the user asks to "retro", "evaluate zforge", "review plugin performance", "score this session", or wants to assess how well zforge's workflow served a feature. Evaluates zforge's workflow scaffolding, not the project's technical decisions or LLM reasoning quality.

Use when working with zforge feature documentation templates, planning features with /plan, tracking progress with /track, or resuming features with /feature-resume. Provides the standard template structure, file ownership rules, and naming conventions.

This skill should be used when the user asks to "orchestrate the feature", "run the phases", "resume implementation", "continue the plan", "the phase agent died", "the agent stopped on its usage limit", "accept this phase", "can these phases run in parallel", or "is this phase done" — and whenever /zforge:feature-orchestrate or /zforge:feature-resume executes. Use it as well when a phase reported done but its evidence was never re-run, or when a long chain is draining the planner's own budget...

Use this agent when a zforge phase has reported DONE and its evidence must be independently verified before the planner accepts it. Typical triggers include $zforge:feature-orchestrate accepting a REPORTED phase during a long chain, and any run where the planner's context is the constrained resource. It reconciles the phase's ## Evidence Required rows against their artifacts, re-executes the rows a trigger selects, and returns an achieved-class table with a per-row verdict and a recommendatio...

Route a concrete reproducible failure through the installed debugging skills; not for open-ended exploration.

Execute an existing zforge feature plan autonomously with phase subagents and evidence-based acceptance.

Resume an existing zforge feature plan interactively, implementing and accepting one phase at a time.

Use this agent when a phase of a zforge feature plan is ready to implement and its work should run in its own context. Typical triggers include $zforge:feature-orchestrate spawning a READY phase, resuming a phase whose agent was interrupted mid-run, and re-running a phase after a decision was rejected in review. See "When to invoke" in the agent body for worked scenarios. Do not use it for work with no phase file — it reads its instructions from one.

Summarize all zforge feature plans, phase counts, and standing flags in the current workspace.

Plan a feature with zforge's completeness contract and write the appropriate requirements or implementation artifact tree.

Check implementation against an existing zforge feature ledger; not for general code review.

Show one zforge feature's phase progress, evidence gaps, standing flags, and open decisions.