Claude Skills

Use when running controlled perf experiments to validate hypotheses.

Use when appending structured perf investigation notes and evidence.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

Use when analyzing plugin structures, MCP tools, and plugin security patterns.

Use when validating task completion before shipping. Runs tests, build, and requirement checks. Returns pass/fail with fix instructions.

Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.

Use when improving agent prompts, frontmatter, and tool restrictions.

Use when improving documentation structure, accuracy, and RAG readiness.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

Use when updating documentation related to recent code changes. Finds related docs, updates CHANGELOG, and delegates simple fixes to haiku.

Use when user asks to \"deep review the code\", \"thorough code review\", \"multi-pass review\", or when orchestrating Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage, specialists), signal detection patterns, and iteration algorithms.

Use when mapping code paths, entrypoints, and likely hot files before profiling.

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.

Use when analyzing doc issues after code changes. Check for outdated references, stale examples, and missing updates.

Use when analyzing plugin structures, MCP tools, and plugin security patterns.

Use when reviewing hooks for safety, timeouts, and correct frontmatter.

Use when generating performance hypotheses backed by git history and code evidence.