[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.

Agent skill for modern Android development with Jetpack Compose — best practices for code generation and review

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.

Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

Agent Skill that analyzes your repo and generates the AI-ready configuration coding agents need — AGENTS.md, copilot-instructions, CI, issue templates, and more. Works in Claude Code, GitHub Copilot, Codex, and Cursor.

General-purpose Playwright automation for coding agents

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

AI-driven quality & governance MCP Server for dbt projects. Audit coverage, profile data, detect schema drift, and auto-generate documentation — all through natural language with your AI assistant.

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

🤖🤮 Hate the yuck codes that agents generated? Try `alint`, a ESLint like toolchain for intent driven code check, freeze your skills, AGENTS.md to lint rules

A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.

MCP server that gives AI coding agents (Claude Code, Cursor, etc.) full control over Unreal Engine 5.7 projects — headless builds & tests, Blueprint editing, actor manipulation, procedural mesh generation, and UE API documentation lookup.

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

Turns AI agents from chaotic code generators into disciplined engineers. 12-stage workflow from research to production.

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.