Browse the library

Give your agent control over your desktop and browser to click, type, and read screens natively.

Plugin that discovers what to measure in your codebase, sets up a benchmark, then runs tree-search experiments with parallel subagents to improve the score.

A collection of 228 battle-tested agent skills for Kotlin and Compose Multiplatform to help AI agents avoid common production traps and footguns.

Engram is an evidence-based learning plugin that turns AI agents into tutors to help humans learn and retain information.

This plugin offers a library of 1285 professional markdown-based agent skills for various AI assistants to perform complex tasks.

This plugin provides AI trading agents with persistent memory, an outcome-weighted decision audit trail, and rule-based trade refusal.

This is an automated index listing over 43,000 Claude Code plugins, their descriptions, and adoption metrics for discovery.

Claude Code plugin bundling specialized agents, skills, hooks and mode commands, installable with one npx command and compatible with Cursor, Codex and more.

This orchestrator allows AI coding agents like Claude Code and Cursor CLI to work together in parallel or sequence within isolated tmux sessions.

This plugin enables natural voice conversations with Claude Code and other MCP-capable agents, allowing hands-free interaction.

A collection of 74 specialized game development skills for AI agents, covering major engines like Godot, Unity, and Unreal.

fluent-korean

snflkd

This Claude Code plugin provides an output style that guides the AI to produce clear and fluent Korean, avoiding common LLM linguistic errors.

This self-hosted AI health data engine consolidates and standardizes lab reports, wearables, and genetic files, allowing an agent to answer questions with cited sources.

This plugin captures, indexes, and makes AI development conversations searchable and shareable, creating reusable skills from chat history.

This set of eleven Claude skills automates LinkedIn account management, including post creation, commenting, replies, profile optimization, and AI output humanization.

This Claude Code plugin enables AI agents to watch and understand videos by extracting frames and processing audio transcriptions with timestamps.

A skills pack or full harness that verifies agent work with stop-hook gates, artifact checks and independent judges across Claude Code, Cursor and Codex.

A method pack for AI agents that enforces architecture-aware planning, evidence-based verification, and technical debt tracking.

This plugin gives AI agents "brain" access to your code repository, enabling grounded Q&A about the codebase with file paths and line numbers.

Provides ADHD-friendly output styles for Claude Code and similar AI agents to make their responses concise, easy to skim, and human-readable.

Syncs AI agent configurations, skills, and context files across Claude Code, Cursor, and Codex, with continuous context refresh and compaction features.

Connects AI agents to Jupyter Notebooks via an MCP server, enabling agents to manage and execute code in notebooks, locally or in the cloud.

A shared knowledge layer for AI agents to persist and query collective learning to avoid repeating mistakes.

This Claude skill allows AI agents to build, test, and interact with iOS applications using Xcode and the iOS Simulator, parsing results effectively.