audit
Verify artifact quality by running coherence lenses (logical consistency) and factual verification tracks (external accuracy). Designed to be loaded by a freshly spawned subagent or nested Claude instance that reads the artifact cold. Produces a findings file — does not fix issues. Use when: after completing a research report, after spec scope freeze, on-demand quality check, verify claims, fact-check, review accuracy, cross-check assertions, post-completion verification for any artifact with evidence-backed claims.
Installation and usage
Verify artifact quality by running coherence lenses (logical consistency) and factual verification tracks (external accuracy). Designed to be loaded by a freshly spawned subagent or nested Claude instance that reads the artifact cold. Produces a findings file — does not fix issues. Use when: after completing a research report, after spec scope freeze, on-demand quality check, verify claims, fact-check, review accuracy, cross-check assertions, post-completion verification for any artifact with evidence-backed claims.
安裝後，您可以透過在終端機執行以下指令來使用此技能：
skills use audit