Developer Tools

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

A comprehensive guide and toolkit for creating effective Claude Code skills. It provides templates, initialization scripts, validation tools, and packaging utilities to help developers build modular extensions that add specialized knowledge, workflows, and tool integrations to Claude Code.

This skill helps developers create and maintain OpenAPI 3.1 specifications for RESTful APIs. It provides comprehensive templates for design-first and code-first approaches, including Python/FastAPI and TypeScript/tsoa examples, along with validation tooling configuration and SDK generation commands.

This skill teaches systematic debugging techniques using the scientific method approach. It covers debugging tools and techniques for JavaScript/TypeScript, Python, and Go, including profiler usage, memory leak detection, binary search debugging with git bisect, and best practices for tracking down elusive bugs in any codebase.

Claude HUD is a statusline plugin for Claude Code that provides a real-time display of your session health. It shows context window usage with color-coded warnings, active tool operations, running agent status, todo progress, git branch information, and API usage limits for Pro/Max/Team subscribers.

This skill provides comprehensive documentation for writing hookify rules - markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. It covers rule file format, event types (bash, file, stop, prompt), regex pattern syntax, advanced conditions, and best practices for organizing rule files.

A comprehensive guide for creating Claude Code plugin hooks that automate validation, context loading, and workflow enforcement. Includes working example scripts for validating file writes and bash commands, plus utility scripts for testing and linting hook implementations before deployment.

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

A comprehensive reference guide for using git worktrees to work on multiple branches simultaneously without stashing changes. It covers creating, managing, and removing worktrees, plus workflow patterns for PR reviews, hotfixes, and comparing implementations across branches.

Doc Reader helps you efficiently consume and navigate external documentation sites without overwhelming your context window. It provides strategies for using llms.txt files, MCP servers for semantic search, and choosing the right approach based on your needs - whether you're exploring, looking for specific APIs, or need comprehensive understanding of a library.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

A debugging methodology skill that applies scientific investigation principles through natural conversation. It guides users through systematic bug diagnosis including hypothesis formation, evidence gathering, root cause analysis, and fix verification while maintaining user control over the investigation direction.