Resolve uncertain product or architecture decisions before implementation. Use for explicit brainstorming or design requests, or when unresolved trade-offs, blast radius, or reversal cost could materially change the implementation; clear, local, reversible work proceeds directly.
Review code and machine-consumed implementation artifacts for defects, risks, quality, correctness, requirements, or standards. Use when the user requests an implementation review, findings, or a review conclusion, including focused reviews. Exclude prose-document review and requests only to read, explain, summarize…
Apply lightweight safeguards when task execution involves completion claims, destructive or external-state changes, debugging, long-running or resumable work, subagent delegation, or high-risk review. Use to preserve evidence, recoverability, and user control without imposing a fixed development workflow.
Locate code ownership and assess repository-map trust from source evidence. Use for unclear ownership, cross-boundary behavior changes, entry-point or dependency changes, or maps that may mislead placement. Also use for explicit map inspection, use, creation, or repair, and dependent-skill repository-context bootstrap…
Review a Markdown design document, consume an accepted fix queue, or independently verify accepted fixes with layered contract extraction, architecture reasoning, adversarial falsification, deterministic evidence gates, risk-based partial re-review, and human-only admission. Use only when the user explicitly invokes…
★not rated 6 3d agoASkillSpector: warn115 tokens
originalMIT
Find and, when mutation is explicitly authorized and repository-aware evidence supports it, remove redundant production surface such as dead or superseded code, duplicated state, unused APIs, speculative abstractions, obsolete compatibility paths, dependencies, packages, tests, and documentation. Use for explicit…
Execute test-driven development through coherent red-green-refactor slices. Use when the user explicitly asks for TDD, test-first, red-green-refactor, or a regression test before fixing a bug. Always pair it with testing-guidelines when adding or changing tests; ordinary test requests use testing-guidelines without…
Design, add, modify, or review automated tests and test strategies using risk-driven evidence selection. Use for unit, integration, regression, and end-to-end test work, including as the test-design companion to TDD. Do not use merely to run existing tests or report their results; this skill does not impose test-first…
Route substantive tasks to the smallest set of explicitly requested or strongly matching skills. Use at task start when skill selection can materially change the process.
★not rated 6 3d agoA32 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: