Ejemplos de Claude Code - Tarjeta de referencia rápida

Comandos rápidos de instalación

Comandos de barra

# Install all
cp 01-slash-commands/*.md .claude/commands/

# Install specific
cp 01-slash-commands/optimize.md .claude/commands/

Memoria

# Project memory
cp 02-memory/project-CLAUDE.md ./CLAUDE.md

# Personal memory
cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md

Skills

# Personal skills
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Project skills
cp -r 03-skills/code-review-specialist .claude/skills/

Subagentes

# Install all
cp 04-subagents/*.md .claude/agents/

# Install specific
cp 04-subagents/code-reviewer.md .claude/agents/

MCP

# Set credentials
export GITHUB_PERSONAL_ACCESS_TOKEN="your_token"
export DATABASE_URL="postgresql://..."

# Install config (project scope)
cp 05-mcp/github-mcp.json .mcp.json

# Or user scope: add to ~/.claude.json

Hooks

# Install hooks
mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

# Configure in settings (~/.claude/settings.json)

Plugins

# Install from examples (if published)
claude --plugin-dir ./07-plugins/pr-review
/plugin install devops-automation
/plugin install documentation

Puntos de control

# Checkpoints are created automatically with every user prompt
# To rewind, press Esc twice or use:
/rewind

# Then choose: Restore code and conversation, Restore conversation,
# Restore code, Summarize from here, or Never mind

Funciones avanzadas

# Configure in settings (.claude/settings.json)
# See 09-advanced-features/config-examples.json

# Planning mode
/plan Task description

# Permission modes (use --permission-mode flag)
# manual         - Ask for approval on every action (config value "default"; "manual" is its alias since v2.1.200)
# acceptEdits    - Auto-accept file edits, ask for others
# plan           - Read-only analysis, no modifications
# auto           - Background classifier decides permissions automatically
# dontAsk        - Only pre-approved tools run; everything else is denied
# bypassPermissions - Accept all actions (--permission-mode bypassPermissions; --dangerously-skip-permissions is equivalent)

# Session management
/resume                # Resume a previous conversation (no args = picker of past sessions)
/rename "name"         # Name the current session
/fork [prompt]         # Copy the conversation into a new background session; keep working here
/subtask <task>        # Spawn a forked subagent that inherits the conversation and reports back
/branch [name]         # Switch into a copy of the conversation, preserving the original
claude -c              # Continue most recent conversation
claude -r "session"    # Resume session by name/ID

Hoja de características Cheat

Casos de uso común

Revisión de código

# Method 1: Slash command
cp 01-slash-commands/optimize.md .claude/commands/
# Use: /optimize

# Method 2: Subagent
cp 04-subagents/code-reviewer.md .claude/agents/
# Use: Auto-delegated

# Method 3: Skill
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Use: Auto-invoked

# Method 4: Plugin (best)
claude --plugin-dir ./07-plugins/pr-review
# Use: /review-pr

Documentación

# Slash command
cp 01-slash-commands/generate-api-docs.md .claude/commands/

# Subagent
cp 04-subagents/documentation-writer.md .claude/agents/

# Skill
cp -r 03-skills/doc-generator ~/.claude/skills/

# Plugin (complete solution)
/plugin install documentation

DevOps

# Complete plugin
/plugin install devops-automation

# Commands: /deploy, /rollback, /status, /incident

Normas del equipo

# Project memory
cp 02-memory/project-CLAUDE.md ./CLAUDE.md

# Edit for your team
vim CLAUDE.md

& Hooks de automatización

# Install hooks (33 events, 5 types: command, http, mcp_tool, prompt, agent)
mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

# Examples:
# - Pre-commit tests: pre-commit.sh
# - Auto-format code: format-code.sh
# - Security scanning: security-scan.sh

# Auto Mode for fully autonomous workflows
claude --permission-mode auto -p "Refactor and test the auth module"
# Or cycle modes interactively with Shift+Tab

Refactorización segura

# Checkpoints are created automatically before each prompt
# Try refactoring
# If it works: continue
# If it fails: press Esc+Esc or use /rewind to go back

Aplicación compleja

# Use planning mode
/plan Implement user authentication system

# Claude creates detailed plan
# Review and approve
# Claude implements systematically

Integración CI/CD

# Run in headless mode (non-interactive). With no permission mode, -p starts in Manual mode
# (config value "default", v2.1.302+): tool calls that need approval are denied, so add
# --allowedTools "Bash(npm test *)" or --permission-mode auto
claude -p "Run all tests and generate report"

# With permission mode for CI
claude -p "Run tests" --permission-mode dontAsk

# With Auto Mode for fully autonomous CI tasks
claude --permission-mode auto -p "Run tests and fix failures"

# With hooks for automation
# See 09-advanced-features/README.md

Aprendizaje y experimentación

# Use plan mode for safe analysis
claude --permission-mode plan

# Experiment safely - checkpoints are created automatically
# If you need to rewind: press Esc+Esc or use /rewind

Equipo de Agentes

# Enable agent teams
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

# Or in settings.json
{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }

# Start with: "Implement feature X using a team approach"

Tareas programadas

# Run a command every 5 minutes
/loop 5m /check-status

# One-time reminder: ask in plain language (/loop repeats until cancelled)
remind me in 30 minutes to check the deploy

Referencia de ubicaciones de archivos

Your Project/
├── .claude/
│   ├── commands/              # Slash commands go here
│   ├── agents/                # Subagents go here
│   ├── skills/                # Project skills go here
│   └── settings.json          # Project settings (hooks, etc.)
├── .mcp.json                  # MCP configuration (project scope)
├── CLAUDE.md                  # Project memory
└── src/
    └── api/
        └── CLAUDE.md          # Directory-specific memory

User Home/
├── .claude/
│   ├── commands/              # Personal commands
│   ├── agents/                # Personal agents
│   ├── skills/                # Personal skills
│   ├── hooks/                 # Hook scripts
│   ├── settings.json          # User settings
│   └── CLAUDE.md              # Personal memory
└── .claude.json               # Personal MCP config (user scope)

System directory/              # macOS /Library/Application Support/ClaudeCode/, Linux /etc/claude-code/, Windows C:\Program Files\ClaudeCode\
├── managed-settings.json      # Managed settings (enterprise/org)
└── managed-settings.d/        # Managed settings drop-ins

Encontrar ejemplos

Por categoría

• Comandos de barra: 01-slash-commands/
• Memoria: 02-memory/
• Skills: 03-skills/
• Subagentes: 04-subagents/
• MCP: 05-mcp/
• Hooks: 06-hooks/
• Plugins: 07-plugins/
• Puntos de control: 08-checkpoints/
• Funciones avanzadas: 09-advanced-features/
• CLI: 10-cli/

Por caso de uso

• Rendimiento: 01-slash-commands/optimize.md
• Seguridad: 04-subagents/secure-reviewer.md
• Ensayos: 04-subagents/test-engineer.md
• Documentación: 03-skills/doc-generator/
• DevOps: 07-plugins/devops-automation/

Por complejidad

• Sencillo: Comandos Slash
• Medio: Subagentes, Memoria
• Avanzada: Skills, Hooks
• Completa: Complementos

Camino de aprendizaje

Día 1

# Read overview
cat README.md

# Install a command
cp 01-slash-commands/optimize.md .claude/commands/

# Try it
/optimize

Día 2-3

# Set up memory
cp 02-memory/project-CLAUDE.md ./CLAUDE.md
vim CLAUDE.md

# Install subagent
cp 04-subagents/code-reviewer.md .claude/agents/

Día 4-5

# Set up MCP
export GITHUB_PERSONAL_ACCESS_TOKEN="your_token"
cp 05-mcp/github-mcp.json .mcp.json

# Try MCP commands
/mcp__github__list_prs

Semana 2

# Install skill
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Let it auto-invoke
# Just say: "Review this code for issues"

Semana 3+

# Install complete plugin
claude --plugin-dir ./07-plugins/pr-review

# Use bundled features
/review-pr
/check-security
/check-tests

Aspectos destacados de las características

Consejos y trucos

Personalización

• Comience con ejemplos como está
• Modificar para adaptarse a sus necesidades
• Prueba antes de compartir con el equipo
• La versión controla sus configuraciones

Mejores prácticas

• Utilice la memoria para los estándares de equipo
• Usar complementos para flujos de trabajo completos
• Usar subagentes para tareas complejas
• Usar comandos de barra para tareas rápidas

Solución de problemas

# Check file locations
ls -la .claude/commands/
ls -la .claude/agents/

# Verify YAML syntax
head -20 .claude/agents/code-reviewer.md

# Test MCP connection
echo $GITHUB_PERSONAL_ACCESS_TOKEN

Matriz de características

Enlaces rápidos

• Guía principal: README.md
• Índice completo: INDEX.md
• Guía original: claude_concepts_guide.md

Cuestiones comunes

P: ¿Qué debo usar? R: Comience con comandos de barra, agregue las características necesarias.

P: ¿Puedo mezclar características? R: ¡Sí! Trabajan juntos. Memoria + Comandos + MCP = potente.

P: ¿Cómo puedo compartir con el equipo? A: Comprometer .claude/ directorio a git.

P: ¿Qué hay de los secretos? R: Utilice variables de entorno, nunca código duro.

P: ¿Puedo modificar ejemplos? R: ¡Por supuesto! Son plantillas para personalizar.

Lista de verificación

Comenzando lista de verificación:

• [ ] Leer README.md
• [ ] Instalar 1 comando de barra
• [ ] Pruebe el comando
• [ ] Crear proyecto CLAUDE.md
• [ ] Instalar 1 subagente
• [ ] Establecer 1 integración MCP
• [ ] Instalar 1 habilidad
• [ ] Pruebe un complemento completo
• [ ] Personalizar para sus necesidades
• [ ] Compartir con el equipo

Inicio rápido: cat README.md

Índice completo: cat INDEX.md

Esta carta: ¡Manténgalo a mano para una referencia rápida!

Última actualización: 26 de octubre de 2026 Versión de Claude Code: 2.1.310 Fuentes: - https://code.claude.com/docs/en/workflows#set-a-size-guideline - https://code.claude.com/docs/en/memory#agents-md - https://code.claude.com/docs/en/changelog - https://code.claude.com/docs/en/cli-reference - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md - https://code.claude.com/docs/en/sub-agents - https://code.claude.com/docs/en/model-config - https://code.claude.com/docs/en/settings - https://code.claude.com/docs/en/hooks - https://code.claude.com/docs/en/env-vars - https://code.claude.com/docs/en/commands - https://code.claude.com/docs/en/remote-control - https://code.claude.com/docs/en/agent-teams - https://code.claude.com/docs/en/memory#storage-location - https://code.claude.com/docs/en/permission-modes - https://code.claude.com/docs/en/managed-settings - https://code.claude.com/docs/en/scheduled-tasks - https://code.claude.com/docs/en/code-review-local - https://code.claude.com/docs/en/changelog#2-1-307 - https://code.claude.com/docs/en/settings-reference#axscreenreader - https://code.claude.com/docs/en/headless - https://code.claude.com/docs/en/permission-modes#tool-calls-denied-in-claude-p-and-agent-sdk-runs - https://code.claude.com/docs/en/tools-reference#session-search-limit - https://code.claude.com/docs/en/routines Modelos compatibles: Claude Fable 5.1, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5