Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
git-workspace-init
Initialize a new git worktree and branch for feature development or bug fixes. Use when: (1) Starting work on a new feature, (2) Beginning a bug fix, (3) Creating an isolated workspace for any task, (4) You want to work in parallel on multiple branches. This skill handles branch naming with conventional branch conventions, worktree creation, and remote push setup.
majiayu000/claude-skill-registry 163
-
mock-strategy-guide
Guides users on creating mock implementations for testing with traits, providing test doubles, and avoiding tight coupling to test infrastructure. Activates when users need to test code with external dependencies.
majiayu000/claude-skill-registry 163
-
notion
Notion API for creating and managing pages, databases, and blocks.
majiayu000/claude-skill-registry 163
-
codex-consensus
Use for multi-perspective analysis with Codex exploring different viewpoints. Triggers on "codex perspectives", "pros and cons from codex", "codex evaluate options", "what are the tradeoffs".
majiayu000/claude-skill-registry 163
-
gam-researcher-agent
Automated context retrieval from Transmission Packet archive using iterative research loop. Implements GAM "Read Path" to complement manual "Write Path" (Memorizer).
majiayu000/claude-skill-registry 163
-
react-observability
Logging, error messages, and debugging patterns for React. Use when adding logging, designing error messages, debugging production issues, or improving code observability. Works for both React web and React Native.
majiayu000/claude-skill-registry 163
-
claude-agent-sdk
Build coding agents with the Claude Agent SDK. Use when creating agentic workflows, implementing todo tracking, monitoring agent progress, building multi-turn conversations, streaming responses, or integrating custom tools with Claude Code.
majiayu000/claude-skill-registry 163
-
process-task-list
Task list management and execution for spec-driven development.
Use when: executing implementation tasks, managing task progress, processing task list with git commits.
Keywords: task execution, process-task, implementation, commit, task management, 任務執行, 實作, 任務清單.
majiayu000/claude-skill-registry 163
-
claude-context-manager
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
majiayu000/claude-skill-registry 163
-
orchestrator-developer
Developer for Claude Orchestrator. Implements tasks according to Tech Lead instructions, applies design tokens, and reports completion. Use when asked to implement code or execute development tasks for the orchestrator.
majiayu000/claude-skill-registry 163
-
api-mitmproxy
Interactive HTTPS proxy for API security testing with traffic interception, modification, and replay capabilities. Supports HTTP/1, HTTP/2, HTTP/3, WebSockets, and TLS-protected protocols. Includes Python scripting API for automation and multiple interfaces (console, web, CLI). Use when: (1) Intercepting and analyzing API traffic for security testing, (2) Modifying HTTP/HTTPS requests and responses to test API behavior, (3) Recording and replaying API traffic for testing, (4) Debugging mobile app or thick client API communications, (5) Automating API security tests with Python scripts, (6) Exporting traffic in HAR format for analysis.
majiayu000/claude-skill-registry 163
-
codex-invocation
Invoke OpenAI Codex CLI with the correct configuration for autonomous code generation. Use when you need Codex to generate or regenerate code files, implement features, or execute multi-step coding tasks.
majiayu000/claude-skill-registry 163
-
skill-name
majiayu000/claude-skill-registry 163
-
cleanup
Archive processed inbox items. Activate when user says "cleanup", "archive inbox". Moves session summaries to archive, keeps inbox clean for new items.
majiayu000/claude-skill-registry 163
-
eslint-flat-config
ESLint 9.x flat configuration patterns. Use when setting up ESLint with TypeScript.
majiayu000/claude-skill-registry 163
-
analyzing-git-sessions
Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.
majiayu000/claude-skill-registry 163
-
fix
Use when review findings need fixing via subagents - invoked by review-loop after each iteration
majiayu000/claude-skill-registry 163
-
iterate-review-with-codex
Activate when user mentions "codex review", "code review", "fix pr code review". This skill provides guidance on how to effectively collaborate with codex to do a interate code review.
majiayu000/claude-skill-registry 163
-
zaregoto-miko
将素材转换为戏言系列葵井巫女子的说话风格。触发场景：(1) 用户提供素材并要求「用巫女子风格改写」「巫女子会怎么说」；(2) 用户说「戏言风格」「巫女子口吻」；(3) 需要将普通文字转换为荒诞比喻 + 活泼语气的风格。
majiayu000/claude-skill-registry 163
-
apify-actor
Build and deploy Apify actors for web scraping and automation. Use for serverless scraping, data extraction, browser automation, and API integrations with Python.
majiayu000/claude-skill-registry 163
-
bd-email
Craft Business Development emails for RYLLC fractional CTO consultancy. Handles warm reconnects, job posting outreach, rejection follow-ups, VC intros, and custom BD scenarios. Uses established templates and project voice.
majiayu000/claude-skill-registry 163
-
smalltalk-developer
Comprehensive Pharo Smalltalk development workflow guide with AI-driven Tonel editing. Provides expertise in Tonel file format syntax (class definitions with name, superclass, instVars, category, method categories, class comment placement), package structure (package.st placement, directory organization, BaselineOf dependencies), development workflow (Edit → Import → Test cycle with absolute paths, re-import timing, test execution), and Pharo best practices (CRC format documentation, method categorization conventions). Use when working with Pharo Smalltalk projects, creating or editing Tonel .st files, organizing packages and dependencies, resolving import order issues, writing class comments, implementing standard Pharo development patterns, or troubleshooting Tonel syntax.
majiayu000/claude-skill-registry 163
-
livekit-prompt-builder
Guide for creating effective prompts and instructions for LiveKit voice agents. Use when building conversational AI agents with the LiveKit Agents framework, including (1) Creating new voice agent prompts from scratch, (2) Improving existing agent instructions, (3) Optimizing prompts for text-to-speech output, (4) Integrating tool/function calling capabilities, (5) Building multi-agent systems with handoffs, (6) Ensuring voice-friendly formatting and brevity for natural conversations, (7) Iteratively improving prompts based on testing and feedback, (8) Building industry-specific agents (debt collection, healthcare, banking, customer service, front desk).
majiayu000/claude-skill-registry 163
-
wt-new
Create a new git worktree and branch for feature development. Use when starting a new feature or story that needs isolated development. Creates worktree in tree/ directory with proper branch setup.
majiayu000/claude-skill-registry 163