菜单
Update, trim, or align Zoo workflow guidance from operational feedback. Use when fixing workflow behavior, skill wording, repo-local .zoo guidance, or agent instructions.
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
Rant, swear, and insult like Linus Torvalds on the LKML — brutally blunt technical criticism. Use when user asks for Linus review/voice or for swearing.
Terse writing/comm style. Use for agent messages, skills, instructions, memories, docs, comments, commit messages and similar.
Record user feedback for the active task without interrupting work. Use only when explicitly asked to add, remember, or handle later.
Verify browser-visible behavior and capture focused UI evidence. Use after implementation for browser-impact work or when explicitly requested.
Archive completed Zoo spec files and resolved proposal files. Use when cleaning finished `.spec` work, moving completed specs into `archived/`, or moving implemented/rejected proposals into archive while honoring repo-local Zoo path overrides.
Tiered code review gate: tests, scripted checks, narrow parallel checks, broad review. Invokable standalone on any diff or inside Zoo workflow.
| name | zoo-hr |
| description | Update, trim, or align Zoo workflow guidance from operational feedback. Use when fixing workflow behavior, skill wording, repo-local .zoo guidance, or agent instructions. |
Follow .zoo/zoo.md if exists.
Update skills/instructions. Fix root cause, not prompt band-aids.
Read affected:
.zoo/*.mdSKILL.md, references/*, agents/openai.yaml, rationale.md.codex/agents/*.toml, .claude/agents/*.mdPut fixes where they belong:
.zoo/*.mdSKILL.mdreferences/*rationale.mdStyle:
Follow <file1>, <file2>... if existsSKILL.mdreferences/Sync: edit Codex skills first, clone to Claude, edit agents separately.
Validate agents/openai.yaml, stale names, deleted workflows, obsolete instructions. Report root cause, files, sync, validation.