ワンクリックで
skill-trace
Inspect local Skills Auditor sensor logs captured by the Skill Trace plugin.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Inspect local Skills Auditor sensor logs captured by the Skill Trace plugin.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Top entry for the Skills Auditor skill system: DEFAULT full pipeline applies filesystem changes (dedup/route/sync use --apply) unless the operator explicitly asks for dry-run or sets SKILLS_AUDITOR_DRY_RUN=1. Sub-skills under skills/. Triggers: /skills-auditor, skills audit, dedup, route, drift, discovery profile.
Skills Auditor cycle 5 (optional) — skills-audit sync with --map-file or sync-discover to plan or apply relinking to canonical skill sources. Sub-skill of skills-auditor.
Skills Auditor cycle 6 — repeat discover audit (prefer --with-drift) to confirm end state after dedup/route/sync. Sub-skill of skills-auditor.
Skills Auditor cycle 2 — skills-audit dedup; top entry defaults to --apply unless dry-run. Hash-aware fold when duplicate names share content. Sub-skill of skills-auditor.
Skills Auditor cycle 1 — discover filesystem state: skills-audit audit (optional --with-drift), drift-check, and optional audit-discovery with a profile file. Sub-skill of skills-auditor.
Skills Auditor cycle 3 — Select-One routing per platform; top entry defaults to --apply unless dry-run. Writes JSON traces under ~/.skills-auditor/traces/. Sub-skill of skills-auditor.
| name | skill-trace |
| description | Inspect local Skills Auditor sensor logs captured by the Skill Trace plugin. |
Use this skill when the user asks about locally captured skill trace or sensor events.
The plugin writes sensor events under .skills-auditor-local/sensors/ in the active working
directory by default. Use the Skills Auditor CLI to inspect them:
skills-audit audit-sensor-logs
skills-audit aggregate-sensor-claims
skills-audit log-stats
Sensor events are raw runtime facts from hooks or transcripts. They do not by themselves prove
semantic skill usage; align them with canonical skill identity before making automation decisions.
Use aggregate-sensor-claims for the first confidence-rated, report-only view.