Browse the library

This skill integrates AI agent's decisions and reasoning directly into Git history, creating a persistent log of development choices and context across sessions.

This plugin provides always-current official Claude API and platform documentation directly within Claude Code, with instant search and interactive courses.

This cookbook provides over 700 AI skills and 36 skill chains for Claude and Cursor, covering diverse areas like PLG, marketing, security, and DevEx, installable with one command.

This skill orchestrates an open-source multi-agent team for product management, with specialized subagents for PM, GTM, QA, and data analysis.

This plugin provides a structured "Plan, Go, Close" workflow with quality gates for AI coding sessions, ensuring agents follow plans and verify changes.

An opinionated multi-agent development framework for Claude Code, based on John Carmack's philosophy, tailored with 10 domain experts for a specific greenfield web stack.

An advanced AI agent orchestration framework for Windows/WSL2, utilizing Kether governance and Pi/MCP to manage isolated workers, LSP tools, task tiering, and subagent delegation for coding tasks.

A self-hosted web platform that generates, stores, and shares AI coding rules for 30 different tools, including Claude Code and Cursor, with team blueprints and a CLI.

A curated collection of 81 production-ready, specialist subagents for Gemini CLI, designed to improve focus, isolate context, and enable tool-scoped delegation for coding tasks.

Provides a Model Context Protocol (MCP) server that learns from your development patterns to give AI coding agents continuous, project-centric context awareness.

A multi-agent framework that uses speculative execution and specialized agents to make AI coding CLIs like Claude Code more cost-effective and faster.

Optimizes OpenClaw agent workflows by providing auto-delegation to sub-agents, cost-aware model routing, and clearer task status to prevent main agent stalls and reduce costs.

A 100% AI-managed, curated awesome list of over 400 Korean AI coding agent skills, categorized for easy discovery across Claude Code, Gemini CLI, Codex, and Cursor.

A Claude Code plugin that transforms the AI agent into a full development team (PM→Lead→Dev→QA) with a pre-configured, role-driven workflow, 44 commands, and auto-learning capabilities.

This web dashboard provides a visual workspace for the pi coding agent, displaying sessions, todos, and subagents, along with observability features.

This resource provides a marketplace and specific plugins for Claude Code, offering tools like a selectable writing style and configuration auditing for AI agents.

This tool provides live, deep observability into Claude Code sessions by visualizing model calls, tool usage, subagents, and context window activity from its logs.

This Claude Code plugin orchestrates a complete AI-native development workflow, from PRD generation and screen specifications to parallel implementation, quality analysis, and verified commits using 11 specialized agents.

This plugin for OpenAI Codex provides development discipline, structured workflows (PABCD), and multi-model subagents, offering 13 specialized dev skills and orchestration for a disciplined development environment.

This Claude Code skill allows users to build production-ready AI agents, skills, and commands from natural language descriptions by analyzing problems and generating configurations.

A Claude Multi-Agent orchestration system that transforms single-threaded AI assistance into a distributed network of self-coordinating sub-agents for complex tasks.

A lazygit-style TUI for Claude Code that allows users to visualize and manage their customizations and plugins, including browsing a marketplace.

A collection of personal Cursor rules that automate coding workflows, manage specifications, tasks, knowledge capture, and code commits for enhanced productivity.

A collection of specialized Claude Code sub-agents designed to manage context efficiency by delegating heavy operations and returning condensed results to the main conversation.