菜单
Execute an existing plan when implementation is authorized and dependent outcomes need tracking; skip short routine checklists.
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
Mandatory newcomer-safe router for every conversation. Classify by action, impact, and named risk; add workflows only when their descriptions match.
Create a durable plan when explicitly requested, required by the High-risk tier, or needed for resumable dependency coordination; skip routine native planning.
Resolve ambiguous product or system work before implementation. Use when materially different interpretations would change scope, architecture, or consequential outcomes; skip precise tasks.
Complete an authorized commit, push, integration, PR, branch, or worktree action while preserving user state. Use after relevant verification when the user or repository requires delivery.
Evaluate incoming code-review feedback against repository evidence. Keep evaluation-only requests read-only; implement supported fixes only when authorized.
Independently review a defined change before integration when requested or when material security, data, concurrency, migration, contract, or cross-module risk warrants it; exclude incoming feedback.
| name | executing-plans |
| description | Execute an existing plan when implementation is authorized and dependent outcomes need tracking; skip short routine checklists. |
A plan's existence or approval to plan does not authorize implementation. Without implementation authority, inspect and report only.
AGENTS.md, and relevant repository state.Treat the plan as an outcome contract, not a transcript. Adapt mechanics when repository reality differs while preserving scope and acceptance. Update a durable plan before continuing only when a material requirement, design, or verification strategy changes.
Later relevant mutations invalidate only affected evidence; rerun those checks before claiming completion.
Resolve recoverable failures with safe diagnostics and alternatives. Ask the user only when missing authority, an architectural choice, or ambiguous requirements would change the result.
Do not invoke another workflow skill solely because a plan exists.