claude-code-guide
Comprehensive guide and skill for Claude Code CLI. Installation, configuration, commands, keyboard shortcuts, MCP integration, sub-agents, and best practices.
How do I install this agent skill?
npx skills add https://github.com/founderjourney/claude-skills --skill claude-code-guideIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is a comprehensive documentation guide for the Claude Code CLI tool by Anthropic. It contains no executable scripts, binaries, or malicious patterns. It provides legitimate installation instructions using trusted official packages and outlines standard configuration procedures.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · No issues
- Runlayerwarn
1/1 file flagged
What does this agent skill do?
Claude Code Guide
Comprehensive reference for Claude Code, Anthropic's official CLI tool for AI-assisted development.
When to Use This Skill
- Learning Claude Code features
- Configuring Claude Code settings
- Understanding keyboard shortcuts
- Setting up MCP servers
- Creating custom sub-agents
- Troubleshooting issues
- Optimizing workflows
Installation
macOS/Linux
npm install -g @anthropic-ai/claude-code
Windows
npm install -g @anthropic-ai/claude-code
Verify Installation
claude --version
Authentication
API Key Setup
# Set API key
export ANTHROPIC_API_KEY="your-key"
# Or via CLI
claude auth login
Check Auth Status
claude auth status
Basic Commands
| Command | Description |
|---|---|
claude | Start interactive session |
claude "prompt" | One-shot query |
claude -c | Continue last conversation |
claude --help | Show help |
Keyboard Shortcuts
Navigation
| Shortcut | Action |
|---|---|
Ctrl+C | Cancel current operation |
Ctrl+D | Exit Claude Code |
Ctrl+L | Clear screen |
↑/↓ | Navigate history |
Editing
| Shortcut | Action |
|---|---|
Ctrl+A | Move to line start |
Ctrl+E | Move to line end |
Ctrl+W | Delete word backward |
Ctrl+U | Delete to line start |
Special
| Shortcut | Action |
|---|---|
Tab | Autocomplete |
Shift+Enter | Multi-line input |
Escape | Cancel current input |
Slash Commands
| Command | Description |
|---|---|
/help | Show help |
/clear | Clear conversation |
/compact | Toggle compact mode |
/model | Change model |
/cost | Show token usage |
/bug | Report a bug |
Configuration
Config File Location
~/.claude/settings.json
Settings Options
{
"model": "claude-sonnet-4-20250514",
"theme": "dark",
"editor": "vscode",
"autoSave": true,
"permissions": {
"allowFileWrite": true,
"allowBash": true,
"allowNetwork": true
}
}
Project Settings
Create .claude/settings.json in project root:
{
"systemPrompt": "You are helping with a Node.js project...",
"allowedPaths": ["src/", "tests/"],
"blockedPaths": ["node_modules/", ".env"]
}
MCP (Model Context Protocol)
What is MCP?
MCP allows Claude to interact with external tools and services through standardized servers.
MCP Configuration
// ~/.claude/mcp.json
{
"servers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-server-filesystem"],
"env": {
"ALLOWED_PATHS": "/home/user/projects"
}
},
"github": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-server-github"],
"env": {
"GITHUB_TOKEN": "${GITHUB_TOKEN}"
}
}
}
}
Available MCP Servers
@anthropic-ai/mcp-server-filesystem- File operations@anthropic-ai/mcp-server-github- GitHub integration@anthropic-ai/mcp-server-postgres- Database queries@anthropic-ai/mcp-server-puppeteer- Browser automation
Sub-Agents
Creating Custom Agents
Create in ~/.claude/agents/:
---
name: code-reviewer
description: Reviews code for best practices
model: claude-sonnet-4-20250514
---
# Code Review Agent
You are a senior code reviewer. When reviewing code:
1. Check for security issues
2. Verify error handling
3. Assess readability
4. Suggest improvements
Be constructive and educational in feedback.
Using Agents
# List agents
claude agents list
# Use specific agent
claude --agent code-reviewer
Skills
Installing Skills
# From marketplace
claude skills install skill-name
# From GitHub
claude skills install github:user/repo
Skill Location
~/.claude/skills/skill-name/SKILL.md
Creating Skills
See skill-creator skill.
Hooks
Pre/Post Hooks
// .claude/hooks.json
{
"preCommand": ["echo 'Starting...'"],
"postCommand": ["echo 'Done!'"],
"preFileWrite": ["backup.sh"],
"postFileWrite": ["format.sh"]
}
Permissions
Permission Levels
ask- Prompt for each actionallow- Allow without promptingdeny- Block action
Configure Permissions
{
"permissions": {
"file:write": "ask",
"bash:execute": "ask",
"network:fetch": "allow"
}
}
Performance Tips
- Use
.claudeignore: Exclude large directories - Project Context: Set in
.claude/folder - Compact Mode: For faster responses
- Specific Prompts: Be precise in requests
- File References: Use
@filenamesyntax
Troubleshooting
Common Issues
"Command not found"
# Reinstall
npm install -g @anthropic-ai/claude-code
# Check PATH
echo $PATH
"Authentication failed"
# Re-authenticate
claude auth logout
claude auth login
"Rate limited"
- Wait and retry
- Check API usage dashboard
- Consider upgrading plan
Debug Mode
claude --debug
Logs Location
~/.claude/logs/
Best Practices
- Clear Context: Start fresh for unrelated tasks
- Incremental Requests: Break large tasks
- Review Changes: Always review file modifications
- Use Git: Commit before major operations
- Custom Instructions: Set project-specific prompts
Resources
Credits
Guide created by zebbern. Licensed under MIT.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/founderjourney/claude-skills/claude-code-guide">View claude-code-guide on skillZs</a>