Code Documentation logo

Code Documentation

CommunityPopular
MoizIbnYousaf
code-documentation

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

Overview

PublisherMoizIbnYousaf
Repositoryai-agent-skills
Skill namecode-documentation
Stars
1.1K
Forks
133
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MoizIbnYousaf on GitHub. Read the source before you install it.

Installation

Install the Code Documentation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MoizIbnYousaf/ai-agent-skills.git /tmp/ai-agent-skills
mkdir -p .claude/skills
cp -r /tmp/ai-agent-skills/skills/code-documentation .claude/skills/code-documentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Documentation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Code Documentation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Code Documentation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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: 'user@example.com',
 *   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

Frequently asked questions

What does the Code Documentation AI skill do?

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

Why use Code Documentation on TypingMind?

Because you install it once and use it with any model. Code Documentation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Code Documentation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/code-documentation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Code Documentation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Code Documentation?

As many as you like. As long as a model supports skills, you can use Code Documentation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Code Documentation AI skill free?

Yes. It is published on GitHub by MoizIbnYousaf under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇