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.
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
Plinth is an AI-native engineering toolkit for modern Java enterprise SDLC, built around reusable Commands, Agents, Skills, and MCP Servers.
Comet: agent skill harness for turning ideas into evaluated workflows
You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command.
A reusable agent workflow kit with personas, skills, rules, and memory files.
The definitive guide & configuration system for GitHub Copilot CLI — agents, skills, rules, multi-AI orchestration, and more
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Skills for controlling Android, iOS and cloud phones
A universal scaffold for AI-assisted game development. 42 agents, 51 commands, 86 skills. Multi-engine (Unity, Unreal, Godot, HTML). Multi-harness (Claude Code, Codex, Cursor, OpenCode, Kiro).
Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is verified done. Works in Claude Code, Cursor, Antigravity, Codex and ZCode.
Self-evolving SDLC enforcement for AI coding agents — hooks, skills, and one-command setup for Claude Code. Plan before coding, test before shipping, escalate when uncertain. Measures itself getting better over time.
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.