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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/alexanderop/afk --skill skill-name命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when the user wants to generate behavioral evals, LLM-judge tests, or eval cases for a skill, agent, prompt, or feature, write a failing eval before implementing, or scaffold an eval harness in a repo that has none
Use when a plan or spec splits into many independently-mergeable units — a codebase-wide migration, rename, or repeated pattern change — and the user wants them implemented in parallel as separate PRs rather than one sequential pass. The fan-out alternative to afk:implement.
Use when the user says "grill me", asks to stress-test a plan, wants to be interviewed or asked the questions needed before building, offers a vague feature idea, or wants grounded planning before non-trivial implementation
基于 SOC 职业分类
正在显示 SKILL.md
| name | skill-name |
| description | Use when [specific trigger, symptom, user request, or workflow state] |
One or two sentences explaining the skill's purpose and core principle. State the invariant this skill protects.
Use this skill when:
Do not use this skill for:
Write steps as commands to the agent. If a step depends on another file, name that file and say exactly when to open it.
STOP and ask the user when:
Do not ask about facts that can be discovered by reading the repo.
| Thought | Reality |
|---|---|
| "[Tempting shortcut]" | [Why it fails and what to do instead] |
| "[Another predictable rationalization]" | [Correct behavior] |
Return this shape:
[Expected final response, artifact, or report format]
If the skill produces a file, name the path pattern and the handoff skill or next workflow step.
related-skill-name - when this skill should defer to it