204 agents available in the Cursor directory
Pre-built AI agents with specialized instructions for specific tasks β from coding and writing to research and analysis. Each agent is ready to deploy with a single click.
Mine your Claude Code and Codex logs into a local you.md agent profile.
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs β write less code, less prose, and denser agent-to-agent handoffs (β53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
Run Claude Design locally as an Agent Skill β Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus 4.8.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders β self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.
β¨ The agentic HTML editor β your local AI agent writes the HTML, you ship it. π 75 Skills Γ 9 Surfaces (magazine Β· deck Β· poster Β· XHS / tweet Β· prototype Β· data report Β· Hyperframes) π‘οΈ Sandboxed preview Β· π€ 1-click to WeChat / X / Zhihu / HTML / PNG π Zero API key β Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.
Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.
Single source of truth for AI agent skills. One folder, all your tools, zero repetition. Write a skill once β easyskillz wires it to Claude Code, Cursor, Codex, Windsurf, Copilot, and Gemini automatically.
Agent Skill for OpenHive β shared knowledge base of AI-discovered solutions. Works with Claude Code, Cursor, VS Code, Kiro, and 35+ tools via the Agent Skills standard.
AI teaching Skill based on the Feynman Technique β makes YOU teach the AI to expose gaps in your understanding. Works with Claude Code, Cursor, Windsurf, and any LLM agent framework.
A curated list of AI-powered coding tools β editors, agents, code review, testing, CLI tools, and more.
A managed AI marketing agent that plugs into all your AI tools. MCP server configs, setup guides, and integrations for Claude, ChatGPT, Cursor, VS Code, and more.
Collective intelligence for AI coding agents. Every fix makes all AI smarter. Works with Claude, Cursor, Copilot, and any AI agent.
Open-source, Docker-ready skill library for AI coding agents. 51+ stateless skills. No database, just workers.
One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Cursor, Aider.
Open source multi-agent harness for orchestrating AI workers. Supports Claude Code, OpenAI Codex, Cursor Agent, and local models.
AI-driven mobile app testing via MCP. Any AI coding agent can test any Android app β no test framework, no boilerplate, no testIDs
A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory β a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
Engineering governance framework for AI coding agents. Forces planning before code, evidence before completion, memory across sessions.
AI-powered WordPress MCP plugin | Give AI agents full access to your pages, themes, files, code, and database through the Model Context Protocol. Built by POSIMYTH.
Runtime failure resolution for coding agents. Hooks into Claude Code, Codex & your favourite harnesses. Catches loops, dangerous actions, and secret leaks before they become incidents. Zero latency. Runs locally.
Security-first AI coding skills for Claude Code, Cursor, and Cline β the only tool that audits your AI agent against OWASP Top 10 + all 6 attack categories in Google DeepMind's AI Agent Traps framework.