Curated collection of agent skills for AI coding assistants.

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

Codex-first Ultracode skill for dynamic coding workflows

CLI that learns repository-specific Claude skills with evolutionary search.

PRB's collection of agent skills

Agent workflow for deadline-bound execution with evidence gates

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

AI-agent skills for distributed-systems testing

Touhou-inspired Agent Skills: distinct, testable, composable problem-solving workflows.

Minimalistic, project-agnostic skills and rules for AI coding agents

Give your AI coding agent a Roblox brain. Skill collection for Roblox Studio game development.

Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

Reusable agent skills for end-to-end software delivery, from requirements and implementation to review, testing, and release.

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

Universal Claude Code workflow plugin with agents, skills, hooks, and commands

General-purpose Playwright automation for coding agents

Minecraft AI agent skills and dual-target plugin bundle for Codex and Claude Code.

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

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