Agent skill · Audited from source

code-documentation

skill · skillcreatorai/ai-agent-skillsMIT licenceAudited 24 Oct 2026 · source a94ded2f83b0

★ 1,153pushed 32 days agoversion 4.1.0
✓SAFEGrade B · 89/100 · 24 Oct 2026 · a94ded2
1,153repo stars · whole skillcreatorai/ai-agent-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit a94ded2f83b0 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “code-documentation (skillcreatorai/ai-agent-skills)”. Retrieved 24 Oct 2026. https://modelsatlas.com/skills/skillcreatorai/code-documentation

3 skills are called “code-documentation”. You are viewing skillcreatorai/ai-agent-skills.

Trust audit

Audit 0.4.1 · source read 24 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha a94ded2f83b0 · 24 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherskillcreatorai GitHub userOwner of the repository this skill is read from
  • Source folderskillcreatorai/ai-agent-skills/skills/code-documentationThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicta94ded2f83b0A new audit runs when the source changes
  • Repository statusNot archivedLast push 32 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

---
name: code-documentation
description: Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.
source: wshobson/agents
license: MIT
version: 4.1.0
---

# Code Documentation

## README Structure

### Standard README Template
```markdown
# Project Name

Brief description of what this project does.

## Quick Start

\`\`\`bash
npm install
npm run dev
\`\`\`

## Installation

Detailed installation instructions...

## Usage

\`\`\`typescript
import { something } from 'project';

// Example usage
const result = something.doThing();
\`\`\`

## API Reference

### `functionName(param: Type): ReturnType`

Description of what the function does.

**Parameters:**
- `param` - Description of parameter

**Returns:** Description of return value

**Example:**
\`\`\`typescript
const result = functionName('value');
\`\`\`

## Configuration

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `option1` | `string` | `'default'` | What it does |

## Contributing

How to contribute...

## License

MIT
```

## API Documentation

### JSDoc/TSDoc Style
```typescript
/**
 * Creates a new user account.
 *
 * @param userData - The user data for account creation
 * @param options - Optional configuration
 * @returns The created user object
 * @throws {ValidationError} If email is invalid
 * @example
 * ```ts
 * const user = await createUser({
 *   email: '[email protected]',
 *   name: 'John'
 * });
 * ```
 */
async function createUser(
  userData: UserInput,
  options?: CreateOptions
): Promise<User> {
  // Implementation
}

/**
 * Configuration options for the API client.
 */
interface ClientConfig {
  /** The API base URL */
  baseUrl: string;
  /** Request timeout in milliseconds @default 5000 */
  timeout?: number;
  /** Custom headers to include in requests */
  headers?: Record<string, string>;
}
```

### OpenAPI/Swagger
```yaml
openapi: 3.0.0
info:
  title: My API
  version: 1.0.0

paths:
  /users:
    post:
      summary: Create a user
      description: Creates a new user account
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UserInput'
      responses:
        '201':
          description: User created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/User'
        '400':
          description: Invalid input

components:
  schemas:
    UserInput:
      type: object
      required:
        - email
        - name
      properties:
        email:
          type: string
          format: email
        name:
          type: string
    User:
      type: object
      properties:
        id:
          type: string
        email:
          type: string
        name:
          type: string
        createdAt:
          type: string
          format: date-time
```

## Inline Comments

### When to Comment
```typescript
// GOOD: Explain WHY, not WHAT

// Use binary search because the list is always sorted and
// can contain millions of items - O(log n) vs O(n)
const index = binarySearch(items, target);

// GOOD: Explain complex business logic
// Users get 20% discount if they've been members for 2+ years
// AND have made 10+ purchases (per marketing team decision Q4 2024)
if (user.memberYears >= 2 && user.purchaseCount >= 10) {
  applyDiscount(0.2);
}

// GOOD: Document workarounds
// HACK: Safari doesn't support this API, fallback to polling
// TODO: Remove when Safari adds support (tracking: webkit.org/b/12345)
if (!window.IntersectionObserver) {
  startPolling();
}
```

### When NOT to Comment
```typescript
// BAD: Stating the obvious
// Increment counter by 1
counter++;

// BAD: Explaining clear code
// Check if user is admin
if (user.role === 'admin') { ... }

// BAD: Outdated comments (worse than no comment)
// Returns the user's full name  <-- Actually returns email now!
function getUserIdentifier(user) {
  return user.email;
}
```

## Architecture Documentation

### ADR (Architecture Decision Record)
```markdown
# ADR-001: Use PostgreSQL for Primary Database

## Status
Accepted

## Context
We need a database for storing user data and transactions.
Options considered: PostgreSQL, MySQL, MongoDB, DynamoDB.

## Decision
Use PostgreSQL with Supabase hosting.

## Rationale
- Strong ACID compliance needed for financial data
- Team has PostgreSQL experience
- Supabase provides auth and realtime features
- pgvector extension for future AI features

## Consequences
- Need to manage schema migrations
- May need read replicas for scale
- Team needs to learn Supabase-specific features
```

### Component Documentation
```markdown
## Authentication Module

### Overview
Handles user authentication using JWT tokens with refresh rotation.

### Flow
1. User submits credentials to `/auth/login`
2. Server validates and returns access + refresh tokens
3. Access token used for API requests (15min expiry)
4. Refresh token used to get new access token (7d expiry)

### Dependencies
- `jsonwebtoken` - Token generation/validation
- `bcrypt` - Password hashing
- `redis` - Refresh token storage

### Configuration
- `JWT_SECRET` - Secret for signing tokens
- `ACCESS_TOKEN_EXPIRY` - Access token lifetime
- `REFRESH_TOKEN_EXPIRY` - Refresh token lifetime
```

## Documentation Principles

1. **Write for your audience** - New devs vs API consumers
2. **Keep it close to code** - Docs in same repo, near relevant code
3. **Update with code** - Stale docs are worse than none
4. **Examples over explanations** - Show, don't just tell
5. **Progressive disclosure** - Quick start first, details later

Excerpt, first 5,761 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit a94ded2

Download folder ↗
npm install

Commands as the repository documents them: shown, never run by us. Our verdict covers commit a94ded2f83b0 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source a94ded2f83b0

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/skillcreatorai/code-documentation/badge.svg)](https://modelsatlas.com/skills/skillcreatorai/code-documentation/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/skillcreatorai/code-documentation/badge.svg)](https://modelsatlas.com/skills/skillcreatorai/code-documentation/)

Questions about code-documentation

What does the code-documentation skill do?
Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills
Is code-documentation safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can code-documentation access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (a94ded2f83b0), read on 2026-10-24. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.