working-with-claude-code
Working with Claude Code
Overview
This skill provides complete, authoritative documentation for Claude Code directly from docs.claude.com. Instead of guessing about configuration paths, API structures, or feature capabilities, read the official docs stored in this skill's references directory.
When to Use
Use this skill when:
- Creating or configuring Claude Code plugins
- Setting up MCP servers
- Working with hooks (pre-commit, session-start, etc.)
- Writing or testing skills
- Configuring Claude Code settings
- Troubleshooting Claude Code issues
- Understanding CLI commands
- Setting up integrations (VS Code, JetBrains, etc.)
- Configuring networking, security, or enterprise features
Quick Reference
| Task | Read This File |
|---|---|
| Create a plugin | plugins.md then plugins-reference.md |
| Set up MCP server | mcp.md |
| Configure hooks | hooks.md then hooks-guide.md |
| Write a skill | skills.md |
| CLI commands | cli-reference.md |
| Troubleshoot issues | troubleshooting.md |
| General setup | setup.md or quickstart.md |
| Configuration options | settings.md |
Documentation Organization
All documentation is stored as individual markdown files in references/. Use the Read tool to access specific documentation:
references/
├── overview.md # Claude Code introduction
├── quickstart.md # Getting started guide
├── setup.md # Installation and setup
├── plugins.md # Plugin development
├── plugins-reference.md # Plugin API reference
├── plugin-marketplaces.md # Plugin marketplaces
├── skills.md # Skill creation
├── mcp.md # MCP server integration
├── hooks.md # Hooks overview
├── hooks-guide.md # Hooks implementation guide
├── slash-commands.md # Slash command reference
├── sub-agents.md # Subagent usage
├── settings.md # Configuration reference
├── cli-reference.md # CLI command reference
├── common-workflows.md # Common usage patterns
├── interactive-mode.md # Interactive mode guide
├── headless.md # Headless mode guide
├── output-styles.md # Output customization
├── statusline.md # Status line configuration
├── memory.md # Memory and context management
├── checkpointing.md # Checkpointing feature
├── analytics.md # Usage analytics
├── costs.md # Cost tracking
├── monitoring-usage.md # Usage monitoring
├── data-usage.md # Data usage policies
├── security.md # Security features
├── iam.md # IAM integration
├── network-config.md # Network configuration
├── terminal-config.md # Terminal configuration
├── model-config.md # Model configuration
├── llm-gateway.md # LLM gateway setup
├── amazon-bedrock.md # AWS Bedrock integration
├── google-vertex-ai.md # Google Vertex AI integration
├── vs-code.md # VS Code integration
├── jetbrains.md # JetBrains integration
├── devcontainer.md # Dev container support
├── github-actions.md # GitHub Actions integration
├── gitlab-ci-cd.md # GitLab CI/CD integration
├── third-party-integrations.md # Other integrations
├── legal-and-compliance.md # Legal information
├── troubleshooting.md # Troubleshooting guide
└── migration-guide.md # Migration guide
Workflow
For Specific Questions
- Identify the relevant documentation file from the list above
- Use Read tool to load:
@references/filename.md - Find the answer in the official documentation
- Apply the solution
Example:
User: "How do I create a Claude Code plugin?"
→ Read @references/plugins.md
→ Follow the official plugin creation steps
For Broad Topics
When exploring a topic, start with the overview document, then drill into specific files:
- Extending Claude Code: Start with
plugins.md,skills.md, ormcp.md - Configuration: Start with
settings.mdorsetup.md - Integrations: Check relevant integration file (vs-code.md, github-actions.md, etc.)
- Troubleshooting: Start with
troubleshooting.md
For Uncertain Topics
Use Grep tool to search across all documentation:
pattern: "search term"
path: ~/.claude/skills/working-with-claude-code/references/
Updating Documentation
The skill includes scripts/update_docs.js to fetch the latest documentation from docs.claude.com.
Run when:
- Documentation seems outdated
- New Claude Code features are released
- Official docs have been updated
node ~/.claude/skills/working-with-claude-code/scripts/update_docs.js
The script:
- Fetches llms.txt from docs.claude.com
- Extracts all Claude Code documentation URLs
- Downloads each page to
references/ - Reports success/failures
Common Patterns
Plugin Development
Read plugins.md for overview, then plugins-reference.md for API details.
MCP Server Setup
Read mcp.md for configuration format and examples.
Hook Configuration
Read hooks.md for overview, then hooks-guide.md for implementation details.
Skill Creation
Read skills.md for the complete skill authoring guide.
What This Skill Does NOT Do
- This skill provides documentation access, not procedural guidance
- For workflows on how to build plugins/skills, use the
extending-claude-codeskill (when available) - This skill is a reference library, not a tutorial
Red Flags
If you find yourself:
- Guessing about configuration file locations → Read
settings.md - Speculating about API structures → Read relevant reference doc
- Unsure about hook names → Read
hooks.md - Making assumptions about features → Search the docs first
Always consult the official documentation before guessing.
More from krosebrook/source-of-truth-monorepo
pydantic ai agent builder
Expert guidance for building AI agents with Pydantic AI framework. Use when creating multi-agent systems, AI orchestration workflows, or structured LLM applications with type safety and validation.
8enterprise erp consultant
Expert guidance for enterprise resource planning systems, business logic, domain modeling, and ERP integration patterns. Use when building ERP systems, implementing business workflows, or integrating with ERP platforms.
8canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
6receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
6test-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass. Activates on phrases like "fix the tests", "tests are failing", or "make the test suite green".
5condition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
5