how

Files (5)

• LICENSE
• SKILL.md
• openai.yaml · agents/
• explainer-prompt.md · references/
• explorer-prompt.md · references/

SKILL.md (first lines)

# 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.

## 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. Explore and explain in one pass in the current context, following `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. When delegation is available and authorized, run independent explorers concurrently using the harness's supported tools and models, each with `references/explorer-prompt.md` and its angle filled in. Give each read access without write authority. Otherwise investigate the same angles sequentially and keep their findings distinct before synthesis; disclose that the exploration was not independent.

## 3. Synthesize (complex only)

Once all exploration angles are complete, synthesize their findings into one explanation from `references/explainer-prompt.md` with every explorer's findings filled in. Use a separate explainer when delegation is available and authorized; otherwise perform a distinct synthesis pass yourself. Verify contradictions against the code.

## 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.

Do not edit project files.

From grugh/skills, MIT.

More from grugh/skills