search
Advanced code search tool that finds definitions, usages, tests, and references across the entire codebase. Use when you need to understand how a symbol is used throughout the project.
Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Advanced code search tool that finds definitions, usages, tests, and references across the entire codebase. Use when you need to understand how a symbol is used throughout the project.
Start a single Gambit game client that connects to 127.0.0.1:1234. Use when the user wants to run a client, test client functionality, or manually connect to a server.
Start the Gambit game server on 0.0.0.0:1234. Use when the user wants to run just the server, test server functionality, or manually test with clients.
Run visual testing where Claude can see the game window and provide inputs
Run pre-commit hooks (clang-format, clang-tidy) on all files. Use when the user wants to format code, run linters, or prepare code for commit.
Build the Gambit game engine (Server and Client executables). Use when the user wants to compile the project, needs to rebuild after code changes, or before running the server or client.
Use usbipd-win to pass through STM32 ST-Link (OpenOCD flashing/debug) and USB-UART dongles (CH340/CP210x/FTDI serial monitor) into WSL2; includes a copy/paste quick workflow for attaching both devices and detai...
Handle MoonBit bit-level parsing and pattern matching over BytesView slices, including using bytes[start:end] and bit patterns like [u1(i), u2(j), ..] or mixed-width fields. Use when extracting or validating pa...
MoonBit single-file mode for .mbt.md files.
Guide for creating effective skills, with MoonBit-specific guidance for skills that use MoonBit packages or tooling. Use when users want to create or update a skill, especially when the skill should include Moo...
Internal worker for pr-review skill. Claims file partitions, fixes comments, resolves threads. NOT for direct user invocation. Spawned only by pr-review orchestrator.
Autonomous multi-agent PR review orchestrator. Spawns parallel workers to process all AI review comments until PR is ready for merge. Supports CodeRabbit, Gemini, Codex, Sourcery, Qodo, Copilot agents. Trigger...
Add a new skill to an existing Claude Code plugin. Use when user wants to create a skill.
Add event hooks to a Claude Code plugin. Use when user wants to run code automatically on events like tool use, session start, etc.
Scaffold a new Claude Code plugin with manifest and directory structure. Use when user wants to create a new plugin.
Add a new subagent to an existing Claude Code plugin. Use when user wants to create an agent.
Comprehensive FastAPI development guide for building production-grade REST APIs. This skill should be used when building FastAPI applications from hello world to production-ready APIs, implementing CRUD operati...
Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Ga...
Production-grade pytest test builder for FastAPI applications with SQLModel. This skill should be used when writing tests for API endpoints, business logic, database operations, or any Python code requiring com...
Production-ready SQLModel patterns for FastAPI applications. This skill should be used when creating database models, writing queries, managing sessions, setting up relationships, configuring connection pools,...
Find and add authoritative source links for all facts, citations, and references in markdown documents
Generate and update release notes for sanhe-claude-code-plugins. Use when user wants to create or update release notes, document version changes, or prepare for a new release. Reads git commit history, pyprojec...
Download YouTube videos as audio files using yt-dlp
Transcribe audio files to text using audinota cli
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.