跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

hk-autonomy-audit

Judge whether an agent could take one area from symptom to verified fix with no person in the loop, and write up the gaps as one committed markdown page in docs/loop_audits/ with a score out of 10. Triggers on: 'loop audit', 'agent readiness', 'could an agent fix this alone', 'can an agent fix this on its own', or /hk-autonomy-audit.

deepklarity · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add deepklarity/harness-kit --skill hk-autonomy-audit

技能说明


name: hk-autonomy-audit description: "Judge whether an agent could take one area from symptom to verified fix with no person in the loop, and write up the gaps as one committed markdown page in docs/loop_audits/ with a score out of 10. Triggers on: 'loop audit', 'agent readiness', 'could an agent fix this alone', 'can an agent fix this on its own', or /hk-autonomy-audit." argument-hint: "[area or flow to audit, e.g. 'spec execution' or 'reflection reports']"

This skill lives in docs/skills/audits/hk-autonomy-audit/. Read docs/skills/audits/hk-autonomy-audit/SKILL.md and follow it exactly.

Every supporting file it mentions (REFERENCE.md, templates, scripts/, examples) sits beside it in that directory. Wherever it says "this skill's directory" or uses a path relative to itself, resolve it against docs/skills/audits/hk-autonomy-audit/.