跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

explain-how

Explain current code with file references and explorer subagents. Use for unfamiliar code or how-it-works questions; use explain-why for history or rationale, or a bare explorer Task for quick lookups.

Cynnamoroll · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add Cynnamoroll/factory-stack --skill explain-how

技能说明


name: explain-how description: "Explain current code with file references and explorer subagents. Use for unfamiliar code or how-it-works questions; use explain-why for history or rationale, or a bare explorer Task for quick lookups." license: MIT compatibility: droid allowed-tools:

  • Read
  • Grep
  • Glob
  • LS
  • Task

Explain how

Give a senior engineer a working mental model, not annotated source. Stay read-only.

1. Size the question

If scope is unclear, state your reading and continue.

  • Simple (one module, one function, a narrow question). Read the code yourself and go to step 3.
  • Complex (a subsystem across files or services, a cross-cutting feature, an architecture overview). Go to step 2.

When in doubt, take the simple path.

2. Explore in parallel

Split the question into 2 to 4 angles, each a distinct slice of the subsystem. Issue one explorer Task per angle, all in one message. Build each prompt from references/explorer-prompt.md with the question and the angle filled in.

3. Write the walkthrough

Merge explorer reports and settle contradictions from code without re-exploring. Follow references/walkthrough-format.md, omitting inapplicable sections.

Done when

  • Every claim about behavior cites a real file:line or symbol you or an explorer read.
  • Open questions the explorers could not trace are listed, not hidden.
  • No file was changed.