Claude Code Expert
Claude Code is Anthropic's agentic coding tool that lives in the terminal and helps turn ideas into code faster. It combines autonomous planning, execution, and validation with extensibility through skills, plugins, MCP servers, and hooks.
When to Use This Skill
Use when users need help with:
- Understanding Claude Code features and capabilities
- Installation, setup, and authentication
- Using slash commands for development workflows
- Creating or managing Agent Skills
- Configuring MCP servers for external tool integration
- Setting up hooks and plugins
- Troubleshooting Claude Code issues
- Enterprise deployment (SSO, sandboxing, monitoring)
- IDE integration (VS Code, JetBrains)
- CI/CD integration (GitHub Actions, GitLab)
- Advanced features (extended thinking, caching, checkpointing)
- Cost tracking and optimization
Activation examples:
- "How do I use Claude Code?"
- "What slash commands are available?"
- "How to set up MCP servers?"
- "Create a new skill for X"
- "Fix Claude Code authentication issues"
- "Deploy Claude Code in enterprise environment"
Core Architecture
Subagents: Specialized AI agents (planner, code-reviewer, tester, debugger, docs-manager, ui-ux-designer, database-admin, etc.)
Agent Skills: Modular capabilities with instructions, metadata, and resources that Claude uses automatically
Slash Commands: User-defined operations in .claude/commands/ that expand to prompts
Hooks: Shell commands executing in response to events (pre/post-tool, user-prompt-submit)
MCP Servers: Model Context Protocol integrations connecting external tools and services
Plugins: Packaged collections of commands, skills, hooks, and MCP servers
Quick Reference
Load these references when needed for detailed guidance:
Getting Started
- Installation & Setup:
references/getting-started.md
- Prerequisites, installation methods, authentication, first run
Development Workflows
Integration & Extension
Configuration & Settings
- Configuration:
references/configuration.md
- Settings hierarchy, key settings, model configuration, output styles
Enterprise & Production
Enterprise Features: references/enterprise-features.md
- IAM, SSO, RBAC, sandboxing, audit logging, deployment options, monitoring
IDE Integration: references/ide-integration.md
- VS Code extension, JetBrains plugin setup and features
CI/CD Integration: references/cicd-integration.md
- GitHub Actions, GitLab CI/CD workflow examples
Advanced Usage
Advanced Features: references/advanced-features.md
- Extended thinking, prompt caching, checkpointing, memory management
Troubleshooting: references/troubleshooting.md
- Common issues, authentication failures, MCP problems, performance, debug mode
API Reference: references/api-reference.md
- Admin API, Messages API, Files API, Models API, Skills API
Best Practices: references/best-practices.md
- Project organization, security, performance, team collaboration, cost management
Common Workflows
Feature Implementation
/cook implement user authentication with JWT
# Or plan first
/plan implement payment integration with Stripe
Bug Fixing
/fix:fast the login button is not working
/debug the API returns 500 errors intermittently
/fix:types # Fix TypeScript errors
Code Review & Testing
claude "review my latest commit"
/test
/fix:test the user service tests are failing
Documentation
/docs:init # Create initial documentation
/docs:update # Update existing docs
/docs:summarize # Summarize changes
Git Operations
/git:cm # Stage and commit
/git:cp # Stage, commit, and push
/git:pr feature-branch main # Create pull request
Design & Content
/design:fast create landing page for SaaS product
/content:good write product description for new feature
Instructions for Claude
When responding to Claude Code questions:
- Identify the topic from the user's question
- Load relevant references from the Quick Reference section above
- Provide specific guidance using information from loaded references
- Include examples when helpful
Loading references:
- Read reference files only when needed for the specific question
- Multiple references can be loaded for complex queries
- Use grep patterns if searching within references
For setup/installation questions: Load references/getting-started.md
For slash command questions: Load references/slash-commands.md
For skill creation: Load references/agent-skills.md
For MCP questions: Load references/mcp-integration.md
For hooks/plugins: Load references/hooks-and-plugins.md
For configuration: Load references/configuration.md
For enterprise deployment: Load references/enterprise-features.md
For IDE integration: Load references/ide-integration.md
For CI/CD: Load references/cicd-integration.md
For advanced features: Load references/advanced-features.md
For troubleshooting: Load references/troubleshooting.md
For API usage: Load references/api-reference.md
For best practices: Load references/best-practices.md
Documentation links:
Provide accurate, actionable guidance based on the loaded references and official documentation.
1---2name: claude-code-23description: Claude Code CLI tool expertise. Features: autonomous coding, slash commands, MCP servers, Agent Skills, hooks, plugins, CI/CD integration. Capabilities: setup/config, troubleshooting, skill creation, MCP integration, enterprise deployment, workflow automation. Actions: configure, troubleshoot, create, deploy, integrate Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, terminal tool, workflow automation, code generation, skill creation, configuration, authentication, API key. Use when: learning Claude Code features, configuring settings, creating skills/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, enterprise deployment questions.4---5
6# Claude Code Expert
7
8Claude Code is Anthropic's agentic coding tool that lives in the terminal and helps turn ideas into code faster. It combines autonomous planning, execution, and validation with extensibility through skills, plugins, MCP servers, and hooks.
9
10## When to Use This Skill
11
12Use when users need help with:
13- Understanding Claude Code features and capabilities
14- Installation, setup, and authentication
15- Using slash commands for development workflows
16- Creating or managing Agent Skills
17- Configuring MCP servers for external tool integration
18- Setting up hooks and plugins
19- Troubleshooting Claude Code issues
20- Enterprise deployment (SSO, sandboxing, monitoring)
21- IDE integration (VS Code, JetBrains)
22- CI/CD integration (GitHub Actions, GitLab)
23- Advanced features (extended thinking, caching, checkpointing)
24- Cost tracking and optimization
25
26**Activation examples:**
27- "How do I use Claude Code?"
28- "What slash commands are available?"
29- "How to set up MCP servers?"
30- "Create a new skill for X"
31- "Fix Claude Code authentication issues"
32- "Deploy Claude Code in enterprise environment"
33
34## Core Architecture
35
36**Subagents**: Specialized AI agents (planner, code-reviewer, tester, debugger, docs-manager, ui-ux-designer, database-admin, etc.)
37
38**Agent Skills**: Modular capabilities with instructions, metadata, and resources that Claude uses automatically
39
40**Slash Commands**: User-defined operations in `.claude/commands/` that expand to prompts
41
42**Hooks**: Shell commands executing in response to events (pre/post-tool, user-prompt-submit)
43
44**MCP Servers**: Model Context Protocol integrations connecting external tools and services
45
46**Plugins**: Packaged collections of commands, skills, hooks, and MCP servers
47
48## Quick Reference
49
50Load these references when needed for detailed guidance:
51
52### Getting Started
53- **Installation & Setup**: `references/getting-started.md`
54 - Prerequisites, installation methods, authentication, first run
55
56### Development Workflows
57- **Slash Commands**: `references/slash-commands.md`
58 - Complete command catalog: /cook, /plan, /debug, /test, /fix:*, /docs:*, /git:*, /design:*, /content:*
59
60- **Agent Skills**: `references/agent-skills.md`
61 - Creating skills, skill.json format, best practices, API usage
62
63### Integration & Extension
64- **MCP Integration**: `references/mcp-integration.md`
65 - Configuration, common servers, remote servers
66
67- **Hooks & Plugins**: `references/hooks-and-plugins.md`
68 - Hook types, configuration, environment variables, plugin structure, installation
69
70### Configuration & Settings
71- **Configuration**: `references/configuration.md`
72 - Settings hierarchy, key settings, model configuration, output styles
73
74### Enterprise & Production
75- **Enterprise Features**: `references/enterprise-features.md`
76 - IAM, SSO, RBAC, sandboxing, audit logging, deployment options, monitoring
77
78- **IDE Integration**: `references/ide-integration.md`
79 - VS Code extension, JetBrains plugin setup and features
80
81- **CI/CD Integration**: `references/cicd-integration.md`
82 - GitHub Actions, GitLab CI/CD workflow examples
83
84### Advanced Usage
85- **Advanced Features**: `references/advanced-features.md`
86 - Extended thinking, prompt caching, checkpointing, memory management
87
88- **Troubleshooting**: `references/troubleshooting.md`
89 - Common issues, authentication failures, MCP problems, performance, debug mode
90
91- **API Reference**: `references/api-reference.md`
92 - Admin API, Messages API, Files API, Models API, Skills API
93
94- **Best Practices**: `references/best-practices.md`
95 - Project organization, security, performance, team collaboration, cost management
96
97## Common Workflows
98
99### Feature Implementation
100```bash
101/cook implement user authentication with JWT
102# Or plan first
103/plan implement payment integration with Stripe
104```
105
106### Bug Fixing
107```bash
108/fix:fast the login button is not working
109/debug the API returns 500 errors intermittently
110/fix:types # Fix TypeScript errors
111```
112
113### Code Review & Testing
114```bash
115claude "review my latest commit"
116/test
117/fix:test the user service tests are failing
118```
119
120### Documentation
121```bash
122/docs:init # Create initial documentation
123/docs:update # Update existing docs
124/docs:summarize # Summarize changes
125```
126
127### Git Operations
128```bash
129/git:cm # Stage and commit
130/git:cp # Stage, commit, and push
131/git:pr feature-branch main # Create pull request
132```
133
134### Design & Content
135```bash
136/design:fast create landing page for SaaS product
137/content:good write product description for new feature
138```
139
140## Instructions for Claude
141
142When responding to Claude Code questions:
143
1441. **Identify the topic** from the user's question
1452. **Load relevant references** from the Quick Reference section above
1463. **Provide specific guidance** using information from loaded references
1474. **Include examples** when helpful
148
149**Loading references:**
150- Read reference files only when needed for the specific question
151- Multiple references can be loaded for complex queries
152- Use grep patterns if searching within references
153
154**For setup/installation questions:** Load `references/getting-started.md`
155
156**For slash command questions:** Load `references/slash-commands.md`
157
158**For skill creation:** Load `references/agent-skills.md`
159
160**For MCP questions:** Load `references/mcp-integration.md`
161
162**For hooks/plugins:** Load `references/hooks-and-plugins.md`
163
164**For configuration:** Load `references/configuration.md`
165
166**For enterprise deployment:** Load `references/enterprise-features.md`
167
168**For IDE integration:** Load `references/ide-integration.md`
169
170**For CI/CD:** Load `references/cicd-integration.md`
171
172**For advanced features:** Load `references/advanced-features.md`
173
174**For troubleshooting:** Load `references/troubleshooting.md`
175
176**For API usage:** Load `references/api-reference.md`
177
178**For best practices:** Load `references/best-practices.md`
179
180**Documentation links:**
181- llms.txt: https://context7.com/websites/claude_en_claude-code/llms.txt?tokens=10000
182 - Search for specific topics: `https://context7.com/websites/claude_en_claude-code/llms.txt?topic=<topic>&tokens=5000`
183 - Eg. Search for "subagent": `https://context7.com/websites/claude_en_claude-code/llms.txt?topic=subagent&tokens=5000`
184- Main docs: https://docs.claude.com/en/docs/claude-code/
185- GitHub: https://github.com/anthropics/claude-code
186- Support: support.claude.com
187
188Provide accurate, actionable guidance based on the loaded references and official documentation.