claude-agent-sdk

loop.js

TypeScript

68

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

launch-your-agent

HTML

85

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

loopkit

Shell

80

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

agent-rules-books

85

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

awesome-gamedev-agent-skills

Python

82

Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.

marketing-studio

JavaScript

82

Agent-driven marketing studio for Claude Code: one /marketing command renders your product's full launch asset suite (logo reveal, demo, launch video, social clips, OG assets)

looper

Python

82

Design visual, review-gated agent loops for Claude Code before you run them.

ECC

JavaScript

95

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

omnigent

Python

85

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

klaatcode

TypeScript

77

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.

dao-code

TypeScript

87

Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.

cc-switch

Rust

90

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

system-prompts-and-models-of-ai-tools

95

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

directional-prompting

72

Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions. Works in Claude Code and Codex CLI.

hermes-agent

Python

85

The agent that grows with you

filetree-skill

Python

67

A Claude Code plugin that maintains `FILETREE.md`.

OpenSwarm

Python

90

Claude code for everything except coding

ponytail

JavaScript

95

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

ego-lite

JavaScript

90

The fastest browser for AI agents to run web automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.

paxm

Go

77

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

AgentsMesh

Go

90

The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.

lazyskills

Go

77

mission control for agent skills

lottie

TypeScript

90

Generate production-ready Lottie animations with Claude Code or Codex

goalbuddy

JavaScript

77

A better /goal for Codex and Claude Code

threejs-game-skills

Python

90

Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.

Brand-building-skills

Shell

72

Brand building skills for Claude Code and AI agents. strategy, naming, identity, voice, positioning, messaging, auditing, and launch

skills

Python

85

Public repository for Agent Skills

self-learning-skills

82

A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.

OpenChatCut

TypeScript

77

Local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.

harness

Swift

77

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

deja-vu

Go

77

Your agents already solved this. deja finds it — memory operations for fifteen coding agents: retroactive search and MCP recall (84.9% R@1 on LongMemEval-S, no LLM), trust scopes, curated notes with tags and lifecycle states, measured impact. One zero-dep binary, fully local.

skills

Python

75

Codebase harness + loop engineer

guard-skills

90

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

delegate-skills

JavaScript

77

Drive Codex, OpenCode, Antigravity, Grok, or Kimi as a background implementer — brief it, review its diff, land the commit yourself.

clawk

Go

82

Give coding agents a disposable Linux VM, not your laptop

OpenTag

TypeScript

82

OpenTag

blitzos

JavaScript

77

BlitzOS allows cloud agents to boot already knowing your work, and keep working with your laptop closed

personal-model

Python

87

Build your HUMAN.md.

codebase-memory-mcp

C

95

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

portaljs

TypeScript

85

🌀 AI-native framework for building data portals. Scaffold a full portal from a brief and load datasets in minutes with agentic skills — any backend (CKAN, GitHub, Frictionless).

dify

TypeScript

95

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

kandev

Go

77

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

mirage

TypeScript

85

The World's First Unified Virtual Filesystem For AI Agents

token-diet

Shell

63

Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.

skills

Python

72

Financial market data consumption skills for claude code and AI agents

claude-pets

TypeScript

68

Claude Code integration for OpenPets: automatic desktop pet status updates with one-command setup.

dothething

Shell

80

an autonomous AI agent: you describe the thing, it does the thing.

loop-engineering

JavaScript

90

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.