# Explain

> >

- **Type:** Skill
- **Install:** `agentstack add skill-ao92265-claude-code-playbook-explain`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ao92265](https://agentstack.voostack.com/s/ao92265)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ao92265](https://github.com/ao92265)
- **Source:** https://github.com/ao92265/claude-code-playbook/tree/main/skills/explain

## Install

```sh
agentstack add skill-ao92265-claude-code-playbook-explain
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Explain Code

Provide a layered explanation that starts simple and goes deeper on request.

## Steps

1. **Identify the target:**
   - Read the file, function, class, or concept the user wants explained
   - If the target is vague ("explain the auth system"), identify the entry point and core files

2. **Layer 1 — One-liner:**
   - Explain what it does in a single sentence
   - Focus on the *what*, not the *how*
   - Example: "This function validates JWT tokens and attaches the decoded user to the request."

3. **Layer 2 — How it works (5-10 lines):**
   - Walk through the high-level flow
   - Name the key steps without implementation details
   - Mention inputs, outputs, and side effects
   - Example: "It extracts the token from the Authorization header, verifies the signature using the secret from env, checks expiration, looks up the user in the database, and attaches them to `req.user`."

4. **Layer 3 — Implementation details (on request):**
   - Walk through the code line by line or block by block
   - Explain *why* specific approaches were chosen
   - Point out error handling, edge cases, and guard clauses
   - Reference related files, types, or functions

5. **Layer 4 — Context and connections (on request):**
   - How this code fits into the larger system
   - What depends on it (callers, consumers)
   - What it depends on (services, libraries, config)
   - Historical context if visible from git blame or comments

6. **Adapt to the reader:**
   - If the user seems experienced: skip basics, focus on non-obvious behavior
   - If the user seems new: use analogies, avoid jargon, explain prerequisites
   - If unclear: default to Layer 2 and offer to go deeper

## Output Format

```
**What it does:** [one-liner]

**How it works:**
1. [step]
2. [step]
3. [step]

**Key details:**
- [non-obvious behavior or edge case]
- [important dependency or assumption]

Want me to go deeper on any part?
```

## Important

- **Start simple, go deep on request.** Don't dump implementation details when the user just wants to understand the purpose.
- **Use the user's language.** If they say "the login thing," use that phrase — don't correct them with "the OAuth2 authentication middleware."
- **Point out the non-obvious.** The obvious parts are already in the code. Explain the *why*, the edge cases, and the gotchas.
- **Be honest about uncertainty.** If the code is unclear or you're guessing at intent, say so.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ao92265](https://github.com/ao92265)
- **Source:** [ao92265/claude-code-playbook](https://github.com/ao92265/claude-code-playbook)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ao92265-claude-code-playbook-explain
- Seller: https://agentstack.voostack.com/s/ao92265
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.