agentleFS
Tony363Tony363/SuperClaude/.claude/skills/sc-document/SKILL.md

sc-document

Skill19 starsChanged 8 months agoMITView on GitHub

Generate focused documentation for components, functions, APIs, and features. Use when creating inline docs, API references, user guides, or technical documentation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Generate: - Create appropriate documentation content

    line 27
  2. Distinctive:

    Integrate: - Ensure compatibility with existing docs

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation Generation Skill

Focused documentation for code, APIs, and features.

Quick Start

# Inline documentation
/sc:document src/auth/login.js --type inline

# API reference
/sc:document src/api --type api --style detailed

# User guide
/sc:document payment-module --type guide

Behavioral Flow

  1. Analyze - Examine component structure and functionality
  2. Identify - Determine documentation requirements and audience
  3. Generate - Create appropriate documentation content
  4. Format - Apply consistent structure and patterns
  5. Integrate - Ensure compatibility with existing docs

Flags

FlagTypeDefaultDescription
--typestringinlineinline, external, api, guide
--stylestringdetailedbrief, detailed

Evidence Requirements

This skill does NOT require hard evidence. Deliverables are:

  • Generated documentation files
  • Inline code comments
  • API reference materials

Documentation Types

Inline (--type inline)

  • JSDoc/docstring generation
  • Parameter and return descriptions
  • Function-level comments

External (--type external)

  • Standalone documentation files
  • Component overviews
  • Integration guides

API (--type api)

  • Endpoint documentation
  • Request/response schemas
  • Usage examples

Guide (--type guide)

  • User-focused tutorials
  • Implementation patterns
  • Common use cases

Style Options

Brief (--style brief)

  • Concise descriptions
  • Essential information only
  • Quick reference format

Detailed (--style detailed)

  • Comprehensive explanations
  • Extended examples
  • Edge case coverage

Examples

Inline Code Docs

/sc:document src/auth/login.js --type inline
# JSDoc with @param, @returns, @throws

API Reference

/sc:document src/api --type api --style detailed
# Full endpoint docs with examples

User Guide

/sc:document payment-module --type guide --style brief
# Quick-start tutorial with common patterns

Component Docs

/sc:document components/ --type external
# README.md for component library

MCP Integration

PAL MCP (Quality & Research)

ToolWhen to UsePurpose
mcp__pal__codereviewAPI docsReview documentation accuracy
mcp__pal__apilookupExternal APIsGet current API documentation
mcp__pal__chatWriting assistanceGet help with complex explanations
mcp__pal__consensusStyle decisionsMulti-model validation of doc approach

PAL Usage Patterns

# Verify documentation accuracy
mcp__pal__codereview(
    review_type="quick",
    step="Reviewing API documentation for accuracy",
    findings="Parameter descriptions, return types, examples",
    relevant_files=["/docs/api/auth.md"]
)

# Get current API docs for external integration
mcp__pal__apilookup(
    prompt="Get current Stripe API documentation for payment intents"
)

# Writing assistance for complex topics
mcp__pal__chat(
    prompt="Help me explain the OAuth2 authorization code flow clearly for developers",
    model="gpt-5.2"
)

Rube MCP (Publishing & Collaboration)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSDoc platformsFind Notion, Confluence, GitBook
mcp__rube__RUBE_MULTI_EXECUTE_TOOLPublishingPush docs to platforms
mcp__rube__RUBE_REMOTE_WORKBENCHBulk docsGenerate docs for large codebases

Rube Usage Patterns

# Publish documentation
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "NOTION_CREATE_PAGE", "arguments": {
        "title": "API Reference: Authentication",
        "content": "## Endpoints\n### POST /auth/login\n..."
    }},
    {"tool_slug": "CONFLUENCE_CREATE_PAGE", "arguments": {
        "space": "DEV",
        "title": "Auth API Documentation",
        "content": "..."
    }}
])

# Notify team of new docs
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {
        "channel": "#documentation",
        "text": "New API docs published: Authentication endpoints"
    }}
])

# Bulk generate docs
mcp__rube__RUBE_REMOTE_WORKBENCH(
    thought="Generate JSDoc for all exported functions",
    code_to_execute='''
import os
# Process all JS files and generate documentation
# Use invoke_llm for each function
'''
)

Flags (Extended)

FlagTypeDefaultDescription
--pal-reviewboolfalseUse PAL to review doc accuracy
--publishstring-Publish via Rube (notion, confluence, gitbook)
--notifystring-Notify via Rube (slack, teams, email)

Tool Coordination

  • Read - Component analysis
  • Grep - Reference extraction
  • Write - Documentation creation
  • Glob - Multi-file documentation
  • PAL MCP - Accuracy review, API lookup, writing assistance
  • Rube MCP - Publishing, notifications, bulk generation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.