playbooks

home / skills / dmdorta1111 / jac-v1 / claude-code

claude-code skill

/.claude/skills/claude-code

This skill helps you install Claude Code, configure MCP servers, and manage agent skills for streamlined coding workflows.

npx playbooks add skill dmdorta1111/jac-v1 --skill claude-code

Review the files below or copy the command above to add this skill to your agents.

Files (16)
skill.md
3.4 KB
---
name: claude-code
description: Activate when users ask about Claude Code installation, slash commands (/cook, /plan, /fix, /test, /docs, /design, /git), creating/managing Agent Skills, configuring MCP servers, setting up hooks/plugins, IDE integration (VS Code, JetBrains), CI/CD workflows, enterprise deployment (SSO, RBAC, sandboxing), troubleshooting authentication/performance issues, or advanced features (extended thinking, caching, checkpointing).
---

# Claude Code

Anthropic's agentic coding tool combining autonomous planning, execution, and validation with extensibility through skills, plugins, MCP servers, and hooks.

## Core Concepts

**Subagents**: Specialized agents (planner, code-reviewer, tester, debugger, docs-manager, ui-ux-designer, database-admin)

**Agent Skills**: Modular capabilities with SKILL.md + bundled resources (scripts, references, assets) loaded progressively

**Slash Commands**: User-defined operations in `.claude/commands/` expanding to prompts

**Hooks**: Event-driven shell commands (SessionStart, PreToolUse, PostToolUse, Stop, SubagentStop)

**MCP Servers**: Model Context Protocol integrations for external tools (GitHub, Jira, databases)

**Plugins**: Packaged collections distributed via marketplace

## Reference Guide

Load references as needed for specific topics:

| Topic | Reference File | Contents |
|-------|----------------|----------|
| Installation & setup | `references/getting-started.md` | Prerequisites, installation methods, authentication |
| Slash commands | `references/slash-commands.md` | Full catalog: /cook, /plan, /fix, /test, /docs, /git, /design |
| Workflow examples | `references/common-workflows.md` | Feature implementation, bug fixing, testing, git ops |
| Creating skills | `references/agent-skills.md` | Skill structure, metadata, bundled resources |
| MCP servers | `references/mcp-integration.md` | Configuration, common servers, authentication |
| Hooks system | `references/hooks-comprehensive.md` | Event types, command/prompt hooks, tool matchers |
| Plugins | `references/hooks-and-plugins.md` | Plugin structure, marketplace, installation |
| Configuration | `references/configuration.md` | Settings hierarchy, model config, output styles |
| Enterprise | `references/enterprise-features.md` | SSO, RBAC, sandboxing, audit logging, deployment |
| IDE integration | `references/ide-integration.md` | VS Code extension, JetBrains plugin |
| CI/CD | `references/cicd-integration.md` | GitHub Actions, GitLab workflows |
| Advanced features | `references/advanced-features.md` | Extended thinking, caching, checkpointing |
| Troubleshooting | `references/troubleshooting.md` | Auth failures, MCP issues, performance, debug mode |
| API reference | `references/api-reference.md` | Admin, Messages, Files, Models, Skills APIs |
| Best practices | `references/best-practices.md` | Project organization, security, performance, cost |

## Instructions

When answering questions:

1. Identify topic from user query
2. Load relevant reference files (use table above)
3. Provide specific guidance with examples
4. For complex queries, load multiple references

**Documentation sources:**
- Context7 llms.txt: `https://context7.com/websites/claude_en_claude-code/llms.txt?tokens=10000`
- Topic search: `https://context7.com/websites/claude_en_claude-code/llms.txt?topic=<topic>&tokens=5000`
- Official docs: https://docs.claude.com/en/docs/claude-code/
- GitHub: https://github.com/anthropics/claude-code
- Support: support.claude.com

Overview

This skill helps developers install, configure, extend, and operate Claude Code for agentic coding workflows. It covers installation, slash commands, creating and managing Agent Skills, MCP server configuration, hooks/plugins, IDE and CI/CD integration, enterprise deployment, and troubleshooting authentication or performance issues. The guidance focuses on practical steps, examples, and links to relevant reference topics.

How this skill works

I inspect the user's intent, load targeted reference topics (installation, slash commands, skills, MCP, hooks, IDE, CI/CD, enterprise, advanced features, troubleshooting), and return concise, task-focused guidance. For complex scenarios I combine multiple references and give concrete commands, config snippets, and troubleshooting steps. I emphasize reproducible workflows and secure defaults.

When to use it

  • Setting up Claude Code locally or on servers (development or production)
  • Adding or customizing slash commands like /cook, /plan, /fix, /test, /docs, /git, /design
  • Building, packaging, or distributing Agent Skills and plugins
  • Integrating external tools via MCP servers (GitHub, Jira, DBs) or custom MCPs
  • Wiring event hooks and plugin hooks for automation around tool use
  • Configuring IDE extensions, CI/CD pipelines, SSO, RBAC, or sandboxing for enterprise

Best practices

  • Start with the official getting-started checklist: verify prerequisites, auth tokens, and network access
  • Modularize capabilities as small skills with clear metadata and bundled test scripts
  • Use MCP servers for external integrations and keep credentials in a secrets store or environment variables
  • Define hooks for predictable lifecycle events (SessionStart, PreToolUse, PostToolUse) and test them locally first
  • Enable audit logging and RBAC in enterprise deployments; isolate agents in sandboxes for untrusted code
  • Automate checks in CI: skill linting, unit tests, and end-to-end verification of slash commands and hooks

Example use cases

  • Install Claude Code on a dev machine, connect to a GitHub MCP, and run /plan to generate a feature plan
  • Create a new Agent Skill for database migrations with bundled migration scripts and test harness
  • Add a hook to run a security scanner (PreToolUse) before any external tool is invoked
  • Integrate Claude Code with VS Code and map slash commands to editor shortcuts for fast iteration
  • Configure CI/CD to run /test and automatic code-review subagent steps on pull requests
  • Deploy in enterprise with SSO, RBAC, sandboxed execution, and centralized audit logging

FAQ

How do I troubleshoot authentication failures with MCP servers?

Verify token scopes, expiration, and network connectivity. Check MCP logs and run diagnostic commands from the reference troubleshooting section. Recreate auth tokens in a secure store and test with a minimal MCP client.

What is the recommended way to test hooks and skills locally?

Use the local debug mode and test harnesses bundled with skills. Trigger lifecycle events (SessionStart, PreToolUse, PostToolUse) manually and validate outputs before deploying to CI or production.