Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
agent-skills
SkillsShared AI agent skills
git clone https://github.com/flurdy/agent-skills.git -
MVP-Prompts
SkillsFree AI prompts and agent skills from the MattVidPro YouTube channel: the prompts used in the videos for AI image, video and music generators, plus ready-to-install skills for Claude Code and Codex.
git clone https://github.com/mattvideoproductions/MVP-Prompts.git -
litestar-skills
SkillsOpinionated first-party agent skills, plugins, subagents, slash commands, and MCP servers for the Litestar framework ecosystem — publishable to Claude Code, Gemini CLI, Codex CLI, Cursor, OpenCode, and VS Code/Copilot from a single repo.
git clone https://github.com/litestar-org/litestar-skills.git -
agent-skills
SkillsAgent skills for building with Archetype AI's Newton — sensor intelligence via /query (fusion, Omega embeddings, data prep, design system)
git clone https://github.com/archetypeai/agent-skills.git -
marketing-skills
SkillsAI marketing skills for research, SEO/GEO, Yandex advertising analytics and expert content. 27 marketing workflows + 14 optional engineering skills.
git clone https://github.com/LuCheremisina/marketing-skills.git -
kluris
SkillsKluris gives AI coding agents shared, human-curated team knowledge: git-backed brains of markdown that agents search and update through per-brain skills and a native CLI.
git clone https://github.com/ngvoicu/kluris.git -
insurance_skills
SkillsSkills used by actuaries and risk managers in their daily work.
git clone https://github.com/open-source-modelling/insurance_skills.git -
agentsync
SkillsSync Claude Code and Cursor rules, skills, and MCP configs from one source of truth. One CLI for Codex, Gemini CLI, and other AI coding agents.
git clone https://github.com/x0c/agentsync.git -
living-docs-skill
SkillsLiving Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.
git clone https://github.com/ejklock/living-docs-skill.git -
last-job-search
SkillsAn AI agent system on Claude Code that runs your whole job search: finds and scores roles, creates and tailors your resume for every role, finds who to message on LinkedIn, and reminds you to follow up.
git clone https://github.com/aranculleton/last-job-search.git -
dsh-iris
SkillsMedia generation and visual understanding for DeepSeek Harness, with multi-provider routing and the integrated Iris workbench.
git clone https://github.com/mokuyoaxis/dsh-iris.git -
jko-claude-plugins
SkillsClaude Code plugin marketplace: Rust, ESP32 C++, Python backend, SwiftUI, dead code detection
git clone https://github.com/johnkozaris/jko-claude-plugins.git -
saas-growth-marketing-skills
SkillsClaude Code skills collection for SaaS growth marketing - 15 skills covering ASO, GEO/SEO, CRO, PLG funnels, retention, pricing, competitor intel, and more.
git clone https://github.com/ekinciio/saas-growth-marketing-skills.git -
google-ads-agent-skills
Skills面向中文广告从业者的 Google Ads AI 工作流:接入AI Agent的配置+广告分析+自动化广告搭建修改 Google Ads AI Workflow for Advertising Professionals: Configuring AI Agent Integration + Ad Analysis + Automated Ad Creation and Editing
git clone https://github.com/Chanlinnn/google-ads-agent-skills.git -
llms.txt
SkillsWhoBot AI (呼波特) llms.txt — Machine-readable company profile for LLM consumption | 面向大模型的企业机器可读档案
git clone https://github.com/whobot-com/llms.txt.git -
skill-provenance
SkillsVersion identity and integrity verification for Agent Skills. Tracks versions, detects staleness, and verifies bundle integrity with SHA-256 hashes across sessions, surfaces, and platforms.
git clone https://github.com/snapsynapse/skill-provenance.git -
humanizer-hu
SkillsMagyar írásstílus-skill agenteknek: a kimenet ne hangozzon AI-nak. Írás közben ad szabályokat, nem a kész szöveget javítja utólag. Csak azt állítja, amit a forrás tartalmaz. 26 minta, dokumentumszintű döntések és LLM nélkül futó lint. Claude Code, Codex, Cursor, Copilot, Gemini CLI és 74 további agent. Hungarian humanizer / anti-AI-slop skill.
git clone https://github.com/Dexxter182/humanizer-hu.git -
AuditorProcessual
SkillsSkill de IA para análise de processos judiciais: lê autos e anexos, organiza fatos e provas, confere fundamentos em fonte oficial e redige peças rastreáveis. Especializada em Direito do Trabalho, com 19 outros ramos. AI skill for Brazilian case analysis and drafting.
git clone https://github.com/lucianumm/AuditorProcessual.git -
agy-ppt
SkillsTurn reports into PowerPoint decks without the AI-slop look. An agent skill purpose-built for the Antigravity + Kiro + Codex pipeline — GPT-image renders dense Traditional Chinese slide text far better than Gemini.
git clone https://github.com/sujunmin/agy-ppt.git -
ai-development-methodology
SkillsMarkdown + git methodology for human and AI software teams: planning, Definition of Done, coordination, handoffs, and verification. Fourteen docs and templates. CC BY 4.0.
git clone https://github.com/Korner83/ai-development-methodology.git -
telegram-cli
SkillsAgent-first Telegram CLI with structured JSON/JSONL and skills for Claude Code, Codex, Antigravity, GitHub Copilot, Grok, Cursor, Amp, and other AI agents.
git clone https://github.com/leynier/telegram-cli.git -
openclaw-genpark-alpha-quant
SkillsAI-powered stock data analysis with fundamental insights and automated trade execution triggers via GenPark protocol.
git clone https://github.com/Alpha-Park/openclaw-genpark-alpha-quant.git -
fondue
Skills🫕 One pot, everyone brings a fork, no double-dipping. A team of AI agents that plan, build and review each other's work, with you as the team lead. Spec-driven development and bug hunting for Claude Code.
git clone https://github.com/jsobolewski1/fondue.git -
ascend-sleuth
Skills昇腾 NPU 训练与推理故障诊断知识库:按症状命中 case、用先验知识与源码分析定位根因,定位后进待审队列、每周升格回库。
git clone https://github.com/pillumina/ascend-sleuth.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.