Browse the library

A tool that converts various sources like documentation sites, GitHub repos, and PDFs into structured knowledge assets and AI skills for platforms like Claude.

ccstatusline

sirmalloc

Add a customizable status line to Claude Code CLI displaying model info, Git status, and token usage.

Track AI coding token usage and costs across tools like Claude Code and Cursor by model, project, and task.

hive

aden-hive

This agent harness provides a model-agnostic runtime for managing colonies of AI agents, enabling reliable and scalable execution of complex business processes.

mcp-use

mcp-use

This TypeScript framework allows developers to build, test, and deploy MCP servers and apps for AI agents like ChatGPT and Claude with full typing and debugging.

A context-engineering framework for AI agents to manage research, planning, and execution phases cleanly.

A self-learning skill layer for Claude Code that distills, updates, and prunes skills from real sessions to keep the agent's knowledge relevant.

This meta-skill for Claude Code designs domain-specific agent teams, defines specialized agents, and generates their skills, supporting various execution modes and quality patterns.

This framework helps build effective and robust AI agents using the Model Context Protocol, offering full MCP support and composable agent patterns.

Enhances 26 AI coding tools like Claude Code and Cursor with 21 curated skills for coding and development workflows, including full Chinese localization.

A curated collection of MCP (Model Context Protocol) resources, clients, and servers, with guides for Chinese users to leverage AI agent capabilities.

Reduce Claude Code token usage by rendering bulky text context into compact images for the model to process.

A trilingual learning roadmap with over 240 curated resources and hands-on examples for agentic AI, from LLM basics to multi-agent systems.

Waza

tw93

A suite of specialized commands like /think and /hunt that teach AI agents disciplined engineering habits for planning, debugging, and UI design.

Connects the ChatGPT web app to Codex via a read-only MCP, allowing ChatGPT to act as the planning and review brain for Codex coding sessions.

A collection of over 175 specialized Codex subagents to enhance AI agent capabilities for various development tasks.

awesome-agent-skills

heilcheng

A community-curated directory of agent skills, tutorials, and guides for various AI assistants like Claude and Codex.

This tool enables AI agents to perform fast and accurate code search in natural language, significantly reducing token usage.

Klavis AI provides MCP integration platforms and SDKs to enable AI agents to reliably use tools and access various integrations, optimizing context windows.

code-graph-rag

vitali87

Allows AI agents to query, understand, and edit multi-language codebases using a knowledge graph built from code structure.

This is a curated list of Agent Skills focused on personal distillation, relationships, commemorative scenes, and methodological perspectives for AI agents.

A curated list of Agent Skills that distill personas, relationships, and methodologies from chats, works, and digital traces into reusable agent skills.

Acts as an AI gateway, registry, and proxy to unify and manage various AI agents, tools, and APIs, optimizing agent workflows and supporting plugins.

skill-recorder

microsoft

This desktop app records user screen activity to generate reusable agent skills or automations by reconstructing intent and steps for Copilot and other Microsoft AI platforms.