10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 670 ms
skillcomposio-community/awesome-claude-pluginsrecord
- perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
- perf-theory-gatherer
skillcomposio-community/awesome-claude-pluginsrecord
- perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
- perf-theory-tester
- web-perf
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
- web-perf
skillcomposio-community/awesome-claude-pluginsrecord
- perf-baseline-manager
Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.
- perf-baseline-manager
skillblockmatic/basilic-skillsrecord
- w-perf
Measure bottlenecks with repository tools, then recommend or apply evidenced optimizations.
- w-perf
skillcomposio-community/awesome-claude-pluginsrecord
- perf-analyzer
Use when synthesizing perf findings into evidence-backed recommendations and decisions.
- perf-analyzer
skillcomposio-community/awesome-claude-pluginsrecord
- perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
- perf-profiler
- 8agentic-perffound in code, not yet checkedno passport yet
MCP serveratheurer/agentic-perf
- submit_gathering_context_result
Submit the dedup gate decision.
- submit_gathering_context_result
skillcomposio-community/awesome-claude-pluginsrecord
- perf-investigation-logger
Use when appending structured perf investigation notes and evidence.
- perf-investigation-logger
skillmohitmishra786/low-level-dev-skillsrecord
- linux-perf
Linux perf profiler skill for CPU performance analysis. Use when collecting sampling profiles with perf record, generating perf report, measuring hardware counters (cache misses, branch mispredicts, IPC), identifying hot functions, or feeding perf data into flamegraph tools. Activates on queries abo
- linux-perf
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.