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.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- 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.
02 资源文件 2
- 参考文档references/explainer-prompt.md3.0 KB
- 参考文档references/explorer-prompt.md2.6 KB
03 SKILL.md 正文
How
Explore the codebase to answer "how does X work?" questions. Produce an architectural explanation that builds a working mental model without annotating the source file by file.
Step 1. Assess complexity
If the scope is ambiguous, state your interpretation and explore. The user can redirect.
- Simple. A single module, a small utility, or another narrow question needs one explanation pass.
- Complex. A subsystem spanning several files or services needs separate exploration angles before synthesis.
When in doubt, take the simple path. Resolve execution through HOST-COMPATIBILITY.md.
Step 2a. Explore a complex question
Split the question into 2 to 4 distinct angles. Dispatch them as how-explorer units. The active profile decides whether the coordinator or read-only workers perform them. Give each unit references/explorer-prompt.md with its angle filled in.
Step 2b. Explain a simple question
Dispatch one shared brief as how-explainer with references/explainer-prompt.md. Omit the explorer-findings section. The active profile decides whether the coordinator or its configured roster performs the work. Go to Step 4.
Step 3. Synthesize a complex question
Dispatch the explorer findings as one how-explainer brief with references/explainer-prompt.md. The coordinator reconciles returned drafts and owns the final explanation.
Step 4. Present
Present the explanation. Edit only for clarity or relevant conversation context.
Use the sections defined in references/explainer-prompt.md and drop any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.
04 同仓库更多 Skills
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Searches available evidence sources and returns a cited account of decisions and tradeoffs. Use how for runtime behavior.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
unslop
Cut AI tells from prose. Use before writing or revising any reply, doc, PR description, commit message, or skill text another reader will see, or for /unslop.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.