SkillAgentSearch skills...

claude-code

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.

Install / Use

npx skills add mrgoonie/claudekit-skills --skill claude-code

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

88/100

Category

Automation

Supported Platforms

Claude Code

Our assessment of claude-code

claude-code scores 88/100 on our quality scale, 1472nd of 2,790 Automation skills we index.

Its SKILL.md is 6.1 KB long, well organised into 19 sections with 6 code examples: a thorough specification that gives an agent plenty to work with.

With 2,218 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
20/20
Description
15/15
Adoption
14/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 8 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-10-31 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 82/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

claude-code compared with similar skills

All 4 of these similar skills score higher than claude-code; compare them before choosing.

SkillScoreStarsUpdatedFormat
claude-code (this skill)by mrgoonie882.2k8mo agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install claude-code?
Run npx skills add mrgoonie/claudekit-skills --skill claude-code. The install tabs above show the steps for each supported agent.
Which AI agents does claude-code work with?
It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
Is claude-code safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 82/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is claude-code still maintained?
The repository was last updated about 8 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

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

  • Slash Commands: references/slash-commands.md

    • Complete command catalog: /cook, /plan, /debug, /test, /fix:, /docs:, /git:, /design:, /content:*
  • Agent Skills: references/agent-skills.md

    • Creating skills, skill.json format, best practices, API usage

Integration & Extension

  • MCP Integration: references/mcp-integration.md

    • Configuration, common servers, remote servers
  • Hooks & Plugins: references/hooks-and-plugins.md

    • Hook types, configuration, environment variables, plugin structure, installation

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:

  1. Identify the topic from the user's question
  2. Load relevant references from the Quick Reference section above
  3. Provide specific guidance using information from loaded references
  4. Include examples when helpful
  5. Reference documentation links from llms.txt when appropriate

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:

  • Main docs: https://docs.claude.com/claude-code
  • GitHub: https://github.com/anthropics/claude-code
  • Support: support.claude.com

Provide accurate, actionable guidance based on the loaded references and official documentation.

Related Skills

View on GitHub
GitHub Stars2.2k
CategoryAutomation
Updated7mo ago
Forks423

Languages

Python

Trust signals

82/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low