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

how

Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

Lauren Tan (poteto) · 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 MindGoblinStudios/grim-tome --skill how

技能说明


name: how description: "Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation." disable-model-invocation: true mutation: true license: MIT source_url: https://github.com/cursor/plugins/blob/main/pstack/skills/how/SKILL.md source_ref: 11713c683fe4add4fd403ea880580abbc9e0875f original_skill: original/UPSTREAM.md metadata: author: Lauren Tan (poteto) pack: pstack lifecycle: beta

Original skill: how from pstack by poteto (MIT) — nested copy at original/UPSTREAM.md.

Beta: manual-only; invoke it by name. Mutation: harness-neutral subagent and model routing (no pstack-models.mdc rule or pinned model slugs), plus a no-subagent fallback.

How

Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.

Spawn every explorer and explainer as a read-only subagent with your harness's subagent tool. If the harness lets you pick models, use a fast coding model for explorers and your strongest reasoning model for the explainer; otherwise inherit the parent's model. If the harness can't spawn subagents, run the same steps yourself in sequence: explore each angle with references/explorer-prompt.md as your checklist, then write the answer with references/explainer-prompt.md.

1. Assess complexity

If the scope is ambiguous, state your interpretation and explore. The user can redirect.

  • Simple (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from references/explainer-prompt.md without the explorer-findings section. Go to step 4.
  • Complex (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.

When in doubt, take the simple path.

2. Explore (complex only)

Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with references/explorer-prompt.md and its angle filled in.

3. Synthesize (complex only)

Once all explorers have returned, spawn one explainer with references/explainer-prompt.md and every explorer's findings filled in.

4. Present

Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.

Output format

The explanation uses the sections defined in references/explainer-prompt.md, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.