From perf
Generates up to 5 performance hypotheses with git history evidence, code path analysis, and confidence levels for specific scenarios.
How this skill is triggered — by the user, by Claude, or both
Slash command
/perf:theoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate performance hypotheses for a specific scenario.
Generate performance hypotheses for a specific scenario.
Follow docs/perf-requirements.md as the canonical contract.
hypotheses:
- id: H1
hypothesis: <short description>
evidence: <file/path or git change>
confidence: low|medium|high
- id: H2
...
2plugins reuse this skill
First indexed Feb 4, 2026
npx claudepluginhub composiohq/awesome-claude-plugins --plugin perfPerforms Maestro-style performance assessments to identify hotspots, regressions, establish baselines, prioritize fixes, and plan optimizations from code and metrics.
Orchestrates performance optimization workflows using static code analysis to detect bottlenecks like N+1 queries, missing indexes, O(n^2) algorithms, blocking I/O, and memory leaks. Accepts profiling data.
Synthesizes performance findings from baselines, experiments, profiling, and hypotheses into evidence-backed summaries, recommendations, and next steps.