Quality

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Guides test-driven development for AI coding agents, ensuring tests are spec-like, seams are confirmed, and the red-green loop produces maintainable tests. Use when building features or fixing bugs test-first.

Moves issues and external pull requests through triage states and roles. Use it to classify, verify, and prepare items with agent-ready or human-ready briefs.

Reviews draft ITU-T Recommendations and ITU-T | ISO/IEC common texts for compliance with official drafting rules, identifying issues before submission. Use for pre-submission audits, structural checks, and formatting verification.

Derive the fidelity ledger and acceptance scenarios from a locked prototype after gate 2b. Use only when a portion is newly locked or re-locked, never before.

Produces a comprehensive slice-exit report when a development slice is believed complete, serving as the definition of 'green' with evidence, audit trail, and methodology checks.

Reviews skill libraries for structural, safety, linkage, size, and trigger-boundary issues. Useful for static analysis of skill metadata and structure without executing code.

Test and measure the activation, outcomes, and routing of agent skills in isolation. Ideal for verifying skill behavior and avoiding false activations.

Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry.