MC-SKILLS

创建或更新 Codex meta-scheduler watcher automation。用于为一个项目、milestone、parent issue、issue set、pull request、PR set、release、repo carrier 或手工目标维护 coordination unit graph、scheduler pool、candidate graph/pool、shared lane lock table、scheduler waiting queue 和调度线程生命周期；在安全并行时创建多个 scheduler thread，并在 shared lane 争用时执行 lane grant / wait / release / recovery。默认中文说明和回报，可适配用户语言；协议字段、状态枚举、工具名和结构化模板字段保持机器可读。

Codex 线程编排的 scheduler 与 worker 协作协议。用于 Codex 作为 scheduler 拆分全局目标、创建或恢复 worker、管理 branch/worktree、发送跨线程指令、运行 gate、完成 closeout；也用于 Codex 作为 worker 确认分配现场、创建并自检 scoped goal、只执行指定 scope、回报 scheduler-readable 关键节点，并等待 scheduler-owned gate。默认使用中文说明和回报，可根据用户语言适配；协议字段、状态枚举、工具名和结构化模板字段保持机器可读。

起草、优化或设置符合 OpenAI《Follow a goal》指南的 Codex goal。起草前先根据最新用户请求确定输出语言。为用户起草可复制的单行 /goal 命令；用户明确要求时，通过 goal 工具/API 创建自包含的 active goal objective。用户使用中文、混合语言或语言不明确时，输出中文。保留命令、路径、代码标识符、URL、issue ID、精确引用，以及 /goal、API、objective、copyable_goal_command、active_goal_api 等标识原文。

Map the architecture of a repository using CodeGraph.

Narrow down likely code locations from bug descriptions using CodeGraph.

Generate a graph-backed implementation plan before modifying repository code.

Build repository context using CodeGraph before starting tasks.

Identify potentially unused or unreachable code using CodeGraph.

Audit module dependencies and detect high coupling or cycles using CodeGraph.

Find application entry points and system startup locations using CodeGraph.

Analyze the impact of modifying, renaming, deleting, or refactoring a symbol, module, API, route or service using CodeGraph.

Evaluate changes to public API surfaces using CodeGraph to avoid breaking consumers.

Plan a safe refactor using CodeGraph analysis.

Identify the minimal set of tests to run after code changes using CodeGraph.

Trace a request or function call from entry point through middleware, controllers, services, repositories and external calls using CodeGraph.

Analyze code smells in a repository, module, directory, file, symbol, or diff and turn findings into engineering decisions. Use when Codex needs to discover candidate code smells, collect evidence such as git churn, size/complexity, tests, dependencies, CodeGraph context, or literals/comments, then decide whether each issue is Fix Now, Refactor Before Next Change, Track as Tech Debt, Accept / Ignore, or Needs Human Judgment. Use for maintainability reviews, tech debt audits, pre-feature refactor decisions, PR risk reviews, architecture smell triage, and issue draft generation. Default to analysis only; do not modify code, create issues, or perform refactors unless explicitly asked.