菜单
Run build/test/lint and read the actual output before claiming done. Use on every implementation task, at the end.
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
Pick the right worker class for each Issue. Use every time you assign an Issue; wrong routing wastes tokens and creates rework.
Break a Company Goal into 3-10 atomic Issues. Use when a Goal arrives with no pre-existing plan and you need to produce a shippable work list.
Ship the smallest change that solves the Issue. Use on every implementation task; scope creep is the default failure mode of executors.
Start implementation with a red test. Use on any bugfix or new behavior — not on refactors or style changes.
Report research results in a form other agents can act on. Use at the end of every Explorer session.
Find files and code patterns fast. Use for every codebase question that starts with "where is X" or "how is Y used".
| name | verify-before-commit |
| description | Run build/test/lint and read the actual output before claiming done. Use on every implementation task, at the end. |
"Looks right" is not verified. Before you write ## Summary and hand off, run the checks and read the output — not paraphrase it.
pnpm build, cargo build). Any failure is automatic FAIL.tsc --noEmit.For each: run the exact command, copy the actual output, note PASS/FAIL.
If a check fails, fix it — do not commit and move on hoping someone else catches it. If the failure is outside your Issue's scope (pre-existing or caused by unrelated environment), note it explicitly in Summary under environment: and leave the Issue open until it's resolved or explicitly de-scoped.
Include build=pass tests=pass lint=pass (or the actual results) in your Summary so the Coordinator doesn't have to re-run them.