Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.
Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec.
Redis' official collection of agent skills

The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
The AI toolkit for building reliable browser automations
Skills to transform AI Agents into GitOps Engineers
Agent Package Manager
Run AI coding agents in hardened container sandboxes.
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.
Composable agent runtime with enforced isolation boundaries
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.
All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!
Publishes localhost services to the agentic web through self-hostable, trustless relays.
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

Deterministic safety solutions for probabilistic AI agents
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
Remote approvals, policy checks, and execution evidence for unattended AI agents.
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。
Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and Claude Code.