菜单
Audit recent regressions in the harness search and identify likely confounds, brittle edits, and safer next-step ideas.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Evolve repo-local Claude Code harness assets through a 5-phase pipeline — harvest context, propose candidate, evaluate with evidence, audit regressions, report results.
Full Meta-Harness status view — Pareto frontier, recent runs, regressions, eval health, installed plugins.
Analyze the current project and generate initial eval tasks for harness optimization. Creates regression and capability eval tasks based on project structure.
Run the evaluation suite on the current harness or a specific candidate run. Reports deterministic check results and LLM-judge assessment.
Summarize the current Meta-Harness-style frontier of harness candidates, including quality, cost, latency, and safety notes.
| name | regressions |
| description | Audit recent regressions in the harness search and identify likely confounds, brittle edits, and safer next-step ideas. |
| context | fork |
| agent | regression-auditor |
| disable-model-invocation | true |
| allowed-tools | Read Grep Glob Bash(mh-regressions *) Bash(find *) Bash(ls *) Bash(cat *) Bash(git diff *) |
Analyze recent regressions in the harness search.
mh-regressions --markdown