.claude/skills/doc-expander/SKILL.md
Expand and enrich documentation using DeepWiki (GitHub repos) and Context7 (libraries). Use when the user wants to research a library/framework, expand existing docs, generate comprehensive documentation from questions, or fill gaps in markdown files. Generates research questions, queries multiple sources, and synthesizes findings into structured documentation.
npx skillsauth add kivo360/omoios doc-expanderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Research and expand documentation using DeepWiki and Context7 MCP servers.
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ 1. Analyze │────>│ 2. Generate │────>│ 3. Research │
│ Existing Doc │ │ Questions │ │ (DeepWiki/C7) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
▼
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ 6. Output │<────│ 5. Structure │<────│ 4. Synthesize │
│ Final Doc │ │ Content │ │ Findings │
└─────────────────┘ └──────────────────┘ └─────────────────┘
User: Expand this README with more details about the API
User: Create comprehensive docs for the fastapi library
Best for: Repository architecture, implementation details, source code patterns
# Get documentation structure
mcp__deepwiki-mcp__read_wiki_structure(repoName="owner/repo")
# Get full documentation
mcp__deepwiki-mcp__read_wiki_contents(repoName="owner/repo")
# Ask specific questions
mcp__deepwiki-mcp__ask_question(
repoName="owner/repo",
question="How does the authentication system work?"
)
When to use DeepWiki:
Best for: Official docs, API references, best practices
# Resolve library ID first
mcp__context7-mcp__resolve-library-id(libraryName="fastapi")
# Then fetch documentation
mcp__context7-mcp__get-library-docs(
context7CompatibleLibraryID="/tiangolo/fastapi",
topic="dependency injection",
mode="code" # or "info" for conceptual content
)
When to use Context7:
| Need | Primary Source | Secondary | |------|---------------|-----------| | API reference | Context7 | DeepWiki | | Code examples | DeepWiki | Context7 | | Architecture | DeepWiki | - | | Best practices | Context7 | DeepWiki | | Troubleshooting | Both | - | | Version changes | Context7 | DeepWiki |
Generate targeted questions to guide research. See references/questions.md for templates.
## Foundation
- What problem does {library} solve?
- What are the core concepts?
- How does it compare to alternatives?
## Architecture
- What is the high-level architecture?
- What are the main components/modules?
- How do components interact?
## Usage
- How do I install and configure it?
- What's the basic usage pattern?
- What are common use cases?
## Integration
- What are the dependencies?
- How does it integrate with {framework}?
- Are there official plugins/extensions?
## Advanced
- How do I handle {specific scenario}?
- What are performance considerations?
- What security practices are recommended?
For comprehensive documentation, use this multi-pass approach:
mcp__context7-mcp__get-library-docs(
context7CompatibleLibraryID=lib_id,
mode="info" # Conceptual overview
)
mcp__context7-mcp__get-library-docs(
context7CompatibleLibraryID=lib_id,
topic="specific_topic",
mode="code" # API and examples
)
mcp__deepwiki-mcp__ask_question(
repoName="owner/repo",
question="How is {feature} implemented internally?"
)
For any remaining questions, query both sources with specific topics.
When expanding, preserve existing content and add:
Structure new documentation with:
# {Library/Topic} Documentation
## Overview
[From Context7 info mode]
## Installation
[From Context7 code mode]
## Quick Start
[Synthesized from both sources]
## Core Concepts
[From both sources]
## API Reference
[From Context7 code mode]
## Examples
[From DeepWiki + Context7]
## Advanced Topics
[From DeepWiki questions]
## Troubleshooting
[From both sources]
## Resources
- [Official Docs](url)
- [GitHub](url)
Use scripts/expand_docs.py for automated expansion:
# Expand a markdown file
python scripts/expand_docs.py docs/api.md --library fastapi
# Generate new documentation
python scripts/expand_docs.py --new --library pydantic --output docs/pydantic.md
# Generate questions only
python scripts/expand_docs.py docs/readme.md --questions-only
development
Spec-driven development workflow for turning feature ideas into structured PRDs, requirements, designs, tickets, and tasks. Uses a state machine approach with EXPLORE → REQUIREMENTS → DESIGN → TASKS → SYNC phases. Each phase has validation gates, checkpointing, and session transcript support for cross-sandbox resumption.
development
Generate comprehensive tests including unit, integration, and property-based tests
development
Spec-driven development workflow for turning feature ideas into structured PRDs, requirements, designs, tickets, and tasks. Uses a state machine approach with EXPLORE → REQUIREMENTS → DESIGN → TASKS → SYNC phases. Each phase has validation gates, checkpointing, and session transcript support for cross-sandbox resumption.
development
Plan safe refactoring with dependency analysis, impact assessment, and rollback strategies