菜单
Use when a loop is stuck, repeating failures, flaking, patching the wrong target, hitting an authority conflict, or burning turns without convergence.
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
Use when auditing a Loop Contract, trace, quality gate, or done claim — or when acting as the independent verifier that grades a loop's success claim and writes verdict.md.
Use when executing an existing Loop Contract by running checks, observing failures, patching, rerunning, updating the trace, and stopping only with evidence.
Use when converting a prose spec, PRD, README, issue, or goal prompt into a Loop Contract with requirements, checks, authority boundaries, stop rules, and trace requirements.
Use when creating, maintaining, auditing, or summarizing loop trace receipts that record checks, failures, patches, rationale, evidence, and stop reasons.
Use when seeding a repository with loop materials such as a goal prompt, Loop Contract, quality gate, trace template, acceptance checklist, and test skeletons.
Use when turning vague requirements into concrete automated checks, visual review gates, manual review items, acceptance tests, or quality-gate commands.
| name | loopify-debug |
| description | Use when a loop is stuck, repeating failures, flaking, patching the wrong target, hitting an authority conflict, or burning turns without convergence. |
Rescue stuck loops.
references/stuck-loop-taxonomy.md.templates/recovery-plan.md.Diagnosis, recovery plan, or blocked/escalated report.
Use loopify-debug on docs/examples/stuck-loop-debug/trace.md and classify why the loop is not converging.