Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From perf
Appends structured perf investigation notes—with exact user quotes, phase summaries, evidence pointers (files/metrics/commands), and decisions—to `{state-dir}/perf/investigations/<id>.md`.
How this skill is triggered — by the user, by Claude, or both
Slash command
/perf:perf-investigation-loggerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Append structured investigation notes to `{state-dir}/perf/investigations/<id>.md`.
Append structured investigation notes to {state-dir}/perf/investigations/<id>.md.
Follow docs/perf-requirements.md as the canonical contract.
## <Phase Name> - <YYYY-MM-DD>
**User Quote:** "<exact quote>"
**Summary**
- ...
**Evidence**
- Command: `...`
- File: `path:line`
**Decision**
- ...
AI_STATE_DIR for state path (default .claude).npx claudepluginhub agent-sh/perf --plugin perf2plugins reuse this skill
First indexed Jul 14, 2026
Records internal investigation logs to `.agent_work/investigations/` with evidence URLs, commands, queries, results, and unknowns. Keeps research separate from polished documents.
Enforces evidence-first debugging for software bugs, incidents, flaky tests, and performance regressions with observation IDs, causality gates, hypothesis tests, and verification rules.
Keeps a TSV decision trail for long-running or unattended work. Each row records what, why, evidence, and result. Useful for reviews after stepping away.