Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Lycheetah-Framework
SkillsPublic method documents. How the work is thought and governed. Self-taught, in Dunedin. Not a commercial offer.
git clone https://github.com/Lycheetah/Lycheetah-Framework.git -
commune-wiki
SkillsA personal wiki engine for Astro with a link graph, a CLI that finds connections while you write, and agent skills that turn dictated dumps into maintained notes. MIT. It runs devon.md.
git clone https://github.com/dmthepm/commune-wiki.git -
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.git -
class-action-finder
SkillsAn AI skill for Claude, Codex, and ChatGPT that scans your email for class action settlements, matches your purchases to open cases, verifies claim links against phishing, and tracks what you filed and got paid.
git clone https://github.com/yingying-chu/class-action-finder.git -
app-factory
SkillsThe skills that build, describe, ship and announce apps — to the App Store and Google Play, and direct on Mac and Windows. A Claude Code plugin marketplace: 42 skills in eight opt-in tracks.
git clone https://github.com/yybd/app-factory.git -
agent-guard
SkillsScan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.
git clone https://github.com/elliottwaves-20/agent-guard.git -
PizzaPi
Skills🍕 An opinionated, extensible Agent Harness based on Pi. Connect Multiple Computers to one harness and work anywhere.
git clone https://github.com/Pizzaface/PizzaPi.git -
ignaciofigueroa.dev
SkillsIf you want to know more about me, check this out
git clone https://github.com/figueroaignacio/ignaciofigueroa.dev.git -
github-bounty-scanner
Skills🛡️ Autonomous GitHub Bounty Scanner & On-Chain Escrow Verifier — Find Real Crypto/USDC/wDOOM Bounties & Filter Fake Scraper Traps
git clone https://github.com/doomsday-network/github-bounty-scanner.git -
centos7-lighthouse
Skills🗼 A lighthouse for CentOS 7 in the AI era — agent-first Claude Code skill + battle-tested toolkit to upgrade CentOS 7 in place to AlmaLinux 10 (ELevate 7→8→9→10) without breaking workloads. 让 CentOS 7 安全原地升级到 AlmaLinux 10,业务不停。
git clone https://github.com/seaworld008/centos7-lighthouse.git -
viber
SkillsA development workflow for Claude Code that takes an idea to committed code.
git clone https://github.com/p2p2sp/viber.git -
designsystem
SkillsDesignsystem for all Elvia websites and apps https://design.elvia.io/
git clone https://github.com/3lvia/designsystem.git -
kanso
SkillsSix Claude Code skills that keep AI-generated code tight. Audit, refactor, commit, PR, curate context.
git clone https://github.com/blakecyze/kanso.git -
minecraftkit
SkillsOffline Minecraft RPG & Paper/Folia API Catalog, Stdio MCP Server, and /mc:* Agent Skills for Claude Code, Cursor, Windsurf, and Codex.
git clone https://github.com/SalyyS1/minecraftkit.git -
req2code
Skills从需求到交付的 AI 编码工作流 Skill:需求分析 → PRD → HTML 原型 → 测试用例 → 开发设计 → 前后端编码 → 联调验收。产物落盘、阶段门禁、支持单阶段停靠,兼容 Claude Code / OpenCode / Codex
git clone https://github.com/wuzt1028/req2code.git -
lemvo
SkillsLemvo — a research agent that thinks and acts. One research system, two CLI engines: Claude Code and Codex CLI.
git clone https://github.com/Yichen-ZJU/lemvo.git -
notebook-video
SkillsAgent Skill for 16:9 Chinese explainer videos: draft-paper narration (everything grows in as it is spoken), five themes, ten teaching blueprints, TTS + one-command Remotion render, 20+ objective gates.
git clone https://github.com/hyt315/notebook-video.git -
agentic-qa-boilerplate
SkillsAgentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.
git clone https://github.com/upex-galaxy/agentic-qa-boilerplate.git -
Agnostic-AI
SkillsYour AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP servers once; apply them identically to Codex, Gemini CLI, Cursor and 16 more. Zero-dependency Node.
git clone https://github.com/ucsandman/Agnostic-AI.git -
ai-powershell-standards
SkillsEnterprise-grade PowerShell development standards, shipped as GitHub Copilot instructions and Claude Code rules, for consistent, secure, and high-quality PowerShell code across teams and projects.
git clone https://github.com/fadwen/ai-powershell-standards.git -
awesome-cad-agent
SkillsA curated list of open-source CAD MCP servers, AI agents, agent skills, and harness plugins.
git clone https://github.com/mlightcad/awesome-cad-agent.git -
legible-film
SkillsVideo editing for coding agents: cut interviews, podcasts and tutorials from their transcripts, make launch films, caption and mix, and check the delivered file before it ships.
git clone https://github.com/JamesDimachkie/legible-film.git -
lightflow
SkillsLightweight, local-first Python DAG workflow compiler and execution engine with human-in-the-loop checkpoints for CLI and AI-agent workflows.
git clone https://github.com/google/lightflow.git -
wavefunction
SkillsOpen-source desktop coding agent for macOS. Use any model: local with Ollama, your own API keys or a ChatGPT sign-in. Parallel chats, MCP connectors, skills, and computer use on a desktop of its own.
git clone https://github.com/stoyan-stoyanov/wavefunction.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.