Browse the library

Provides a single-file set of rules for AI agents to prevent over-engineering, promoting simpler and more direct solutions.

Composable skills that make AI coding assistants follow a design-first workflow from requirements to implementation and review, with project standards kept in a .lattice folder.

Claude Code plugin with 100+ skills, agents and hooks that enforce review gates and verifiable completion, with skills-only install for Codex, Cursor and others.

Allows Claude Code users to switch between and delegate tasks to ChatGPT, Cursor, OpenCode Zen, Antigravity, and Grok models within one session.

Orchestrates local subagents for Codex and Claude, providing persistent task states, reusable teams, and interruption recovery.

A toolkit of three Agent Skills to mine workflows, personalize existing skills, and generalize personal skills for public sharing.

Provides a methodology and skills to build products with AI agents that remember, by turning documentation into a navigable knowledge graph.

Provides reusable agentic loops as open-standard Agent Skills for tasks like autoresearch, data analysis, and code optimization.

Offers a collection of 23 agent skills and safety hooks for AI-driven software development across multiple coding agents.

RecallLoom provides persistent project memory for AI agents, saving context, decisions, and next steps in local project files without a database.

Flompt is a visual AI prompt builder that lets users decompose prompts into a flowchart, edit them, and recompile into Claude-optimized XML.

Yume provides a native desktop UI for Claude Code, offering advanced orchestration, live thinking, background agents, and multi-provider support.

This is a curated directory of over 100 sub-agent prompts and MCP servers for Claude Code, searchable by category and keyword.

Clodfarm orchestrates multiple Claude Code agents to autonomously build, deploy, market, and monetize applications using AWS, Stripe, and Google Ads.

An open, benchmark-validated context format that defines rules and boundaries for AI coding agents to ensure consistent behavior across codebases.

A fully functional web workspace for Claude Code CLI, offering chat, Kanban, task scheduling, and multi-agent orchestration.

Provides agent skills for Codex OS and other agents, enabling persistent knowledge, verification, scheduled loops, and multi-agent orchestration.

Offers practical recommendations and plugins to enhance AI-assisted development workflows using Claude Code.

An opinionated macOS bootstrap that sets up Claude Code and Codex with skills, plugins, rules, global CLAUDE.md/AGENTS.md and hardened dotfiles.

A command center to orchestrate context switching and manage multiple AI coding agent harnesses from the terminal interface.

Provides a real-time TUI sidebar for monitoring sub-agents' status, token usage, costs, and progress within OpenCode.

Integrates with Linear to allow Claude Code agents to manage issues, projects, and teams using MCP tools and GraphQL API patterns.

Allows Claude Code to delegate complex coding, review, and research tasks to Google Antigravity sub-agents, saving tokens and enabling parallel work.

Provides agentic-first Cursor Rules with advanced reasoning and tool orchestration protocols for AI coding using MiniMax M3.