Library
88,751 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
dotforge
SkillsConfiguration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.
Source for dotforge (opens github.com) git clone https://github.com/luiseiman/dotforge.git -
rei-skills
SkillsThe engineering-grade skill layer for AI agents. 895 validated skills, 21 AI adapters, workflows & REI Reverse Engineering (REA) for Claude, Codex, Cursor & Copilot.
Source for rei-skills (opens github.com) git clone https://github.com/rootcastleco/rei-skills.git -
BotArmor: LLM red teaming for chatbots
MCP serversLLM red teaming and prompt injection testing for chatbots and AI agents: A-F grade, prompt fixes.
Source for BotArmor: LLM red teaming for chatbots (opens github.com) @botarmor/mcp@0.1.2 -
squidbrake
SkillsAgents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a teammate's sign-off, every action on a tamper-evident record. Open source.
Source for squidbrake (opens github.com) git clone https://github.com/batrapulkit/squidbrake.git -
deslop
SkillsPlain-English legal writing skill for AI agents (Claude Code, Codex, Antigravity). For lawyers, paralegals, and in-house counsel: audits and rewrites legalese and AI slop in contracts, briefs, memos, and client letters into clear prose using Garner's plain-language rules, while preserving legal terms of art.
Source for deslop (opens github.com) git clone https://github.com/fayerman-source/deslop.git -
ai-skills-agents-context
SkillsClaude Code agents, skills, and reference guides: security, code-quality and WCAG accessibility auditors, Gemini/GPT/Grok consult agents, and in-depth guides to Agent Skills and MCP.
Source for ai-skills-agents-context (opens github.com) git clone https://github.com/ventz/ai-skills-agents-context.git -
academic-students
SkillsA complete study toolkit for AI assistants — Claude, Codex, Gemini CLI, Cursor, Copilot: assignment coaching, professor-style grade estimates, academic writing, exam prep, lecture notes, study planning and Moodle/Canvas sync for every student.
Source for academic-students (opens github.com) git clone https://github.com/Noam-Marom/academic-students.git -
skills
SkillsProfessional skills for any work and software factory, nasty bugs, hard decisions and reliable software delivery with Claude Code, Codex and other AI agents.
Source for skills (opens github.com) git clone https://github.com/simonasrazm/skills.git -
naturalizacion-texto-es
SkillsSkill para Claude Code que naturaliza texto en español generado por IA: 11 técnicas lingüísticas y detección de marcas técnicas/tipográficas (watermarking, caracteres invisibles), orientadas a calidad editorial, no a evasión de detectores.
Source for naturalizacion-texto-es (opens github.com) git clone https://github.com/dorelysm/naturalizacion-texto-es.git -
prp-manager
SkillsAgent Skill for creating and executing PRPs (Product Requirements Prompts) using Context Engineering principles. Works with Claude Code, Cursor, Windsurf, and other compatible agents.
Source for prp-manager (opens github.com) git clone https://github.com/willywg/prp-manager.git -
neo-agent-skills
SkillsThe working rules (skills) the cross-model Neo.mjs agent team loads every session: ticket intake, PR review gates, lane coordination and guards, versioned as one package. For apps built on Neo.mjs, for contributors, and for anyone who wants to read them.
Source for neo-agent-skills (opens github.com) git clone https://github.com/neomjs/neo-agent-skills.git -
OpenRouter: Fusion
ModelsFusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...
Source for OpenRouter: Fusion (opens openrouter.ai) openrouter/fusion -
zh-tw-humanizer
Skills繁體中文(台灣)去 AI 味 skill:62 種 AI 寫作特徵、157 組兩岸用語在地化、事實保留檢查(--source)、33 案例 eval 對照實測(0.99 vs 0.86)。Traditional Chinese (Taiwan) humanizer for Claude Code / Codex / Cursor, with a measurable no-fabrication check.
Source for zh-tw-humanizer (opens github.com) git clone https://github.com/acchuang/zh-tw-humanizer.git -
grimoire
SkillsPackage manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie, and opencode — pinned by digest in a lockfile. Storage is any OCI registry; there is no service to run.
Source for grimoire (opens github.com) git clone https://github.com/grimoire-rs/grimoire.git -
MCP-Plugin-dotnet
MCP servers.NET MCP bridge: expose app methods/data as MCP tools, prompts, and resources via an in-app plugin + lightweight server (SignalR; stdio/http).
Source for MCP-Plugin-dotnet (opens github.com) git clone https://github.com/IvanMurzak/MCP-Plugin-dotnet.git -
slides-ai-plugin
SkillsSlides AI Plugin for Claude, OpenClaw, etc that turns any idea into a full presentation — animated HTML or editable PowerPoint — from a single prompt
Source for slides-ai-plugin (opens github.com) git clone https://github.com/proyecto26/slides-ai-plugin.git -
Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc
Source for universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex (opens github.com) git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git -
maw
SkillsAdversarial multi-agent pipeline for Claude Code and Codex CLI: planning, plan review, implementation, cross-model code review, QA. Installable skills, no runtime.
Source for maw (opens github.com) git clone https://github.com/pockerhead/maw.git -
awesome-story-skills
Skills能直接装、直接用的 AI 写故事开源工具(不是论文清单):小说、网文、剧本、短剧、跑团、同人和非虚构叙事的 skill、应用和框架,按叙事方法分类 · Ready-to-use open-source tools for LLM storytelling, not a paper list: skills, apps and harnesses for novels, scripts, interactive fiction, roleplay and narrative nonfiction, sorted by method
Source for awesome-story-skills (opens github.com) git clone https://github.com/UnderleveledBuilder/awesome-story-skills.git -
tyran
Agents & frameworksA task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
Source for tyran (opens github.com) git clone https://github.com/jjanczur/tyran.git -
videoexpress-scripting-skill
SkillsClaude skill for scripting multi-clip AI videos in VideoExpress 3.5: multishot prompts, Create Mode styles, chaining and failure-mode fixes. CC BY-NC 4.0.
Source for videoexpress-scripting-skill (opens github.com) git clone https://github.com/ratava/videoexpress-scripting-skill.git -
ai-crawler-py
Agents & frameworksCrawl a website starting from a URL, find relevant pages, and extract data – all guided by your natural language prompt.
Source for ai-crawler-py (opens github.com) git clone https://github.com/oxylabs/ai-crawler-py.git -
orchestra-auto
SkillsAn Orca best practice built around Matt Pocock's engineering skills. His chain stays: grill-with-docs, to-spec, to-tickets, then implement or implement-spec, closing with code-review. Orca supervises each step in its own worktree, with gates and merge. Not affiliated with or endorsed by Matt Pocock.
Source for orchestra-auto (opens github.com) git clone https://github.com/whutlichao/orchestra-auto.git -
Alex_Skill_Mall
SkillsCurated GitHub Copilot plugin marketplace: 363 installable plugins plus a trust-scored discovery index across 3,862 plugins in 42 stores. Start with Alex ACT Core.
Source for Alex_Skill_Mall (opens github.com) git clone https://github.com/fabioc-aloha/Alex_Skill_Mall.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.