Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
hackathon-flow
Skills黑客松从报名到领奖的工程脚手架:一张路线图看完 19 份详规 + 42 个模板 + 7 份填好的示例,丢给 Claude Code / Codex 就能开工。四道门、F 点冻结、评分表赛后才给怎么救、多 Agent 靠文件接力——零基础也能从 0 到 1,打完复盘成下一场的资产。
git clone https://github.com/fqyy360t/hackathon-flow.git -
awesome-ai-media-skills
SkillsA curated list of Claude Code skills, MCP servers, and AI agent capabilities for video creation, social media management, and content automation.
git clone https://github.com/JuneYaooo/awesome-ai-media-skills.git -
skills
SkillsVideo skills for Claude Code, Codex, Grok, Cursor and Gemini CLI: 83 AI video skills for UGC ads, product videos, music videos, consistent characters, captions, motion graphics and FFmpeg edits. Seedance 2.5, Kling 4, Veo 3.1, GPT Image 2.6 and ElevenLabs on one key, or free and local.
git clone https://github.com/vargHQ/skills.git -
obsidian-vault-agent
SkillsClaude Code plugin: AI agent for your Obsidian vault — process books, courses, papers, YouTube into connected notes
git clone https://github.com/tuan3w/obsidian-vault-agent.git -
mirage-engine
SkillsA code-only world engine for AI agents: build whole towns and landscapes in three.js as code (pre-alpha)
git clone https://github.com/paraldaMeta/mirage-engine.git -
Raycast-AI-Skill
SkillsAn AI agent skill that builds Raycast extensions, scripts, and commands the right way, the first time.
git clone https://github.com/adriangrantdotorg/Raycast-AI-Skill.git -
esri-developer-agent-skills
SkillsAgent skills for working with ArcGIS
git clone https://github.com/Esri/esri-developer-agent-skills.git -
jeffy-loop
SkillsA Claude Code loop that finds bugs in your repo, fixes them, and checks every fix before it commits.
git clone https://github.com/lenamonj/jeffy-loop.git -
vita-agent-use
SkillsLet an AI agent use your PS Vita.
git clone https://github.com/shoui520/vita-agent-use.git -
skillmaxxing
SkillsSelf-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.
git clone https://github.com/Bennyoooo/skillmaxxing.git -
the-librarian
SkillsSkill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.
git clone https://github.com/aka-kika/the-librarian.git -
OpenSocrates
Skills48 open reasoning methods for Claude, Codex and Antigravity. Check assumptions, compare options and revisit decisions. Instructions in 10 languages.
git clone https://github.com/ParkerHwang/OpenSocrates.git -
forge-of-thought
SkillsForge of Thought is an AI cognitive extension: a workshop where your idea is forged into a decision you can stand behind. You and the AI elicit the idea together until it is whole, reviewers that never saw the conversation attack it, and who decided what and why is recorded. Runs in Claude Code.
git clone https://github.com/pche-broken-artist/forge-of-thought.git -
QAMap
SkillsLocal pull-request review brief for coding agents: the diff, the tests and callers of changed code, and change signals in one report. No LLM call, no upload. Claude Code used 44% fewer tokens with it on 42 public PRs.
git clone https://github.com/IvoryCanvas/QAMap.git -
stitch-kit
SkillsYour coding agent designs terrible UI. stitch-kit wires it into Google Stitch MCP and teaches it the whole pipeline — ideation, screen generation, design systems, production components.
git clone https://github.com/gabelul/stitch-kit.git -
crow
SkillsCROW is a collection of agents and skills for agentic software development.
git clone https://github.com/bcgov/crow.git -
ai-security-research-radar
SkillsAI Security Research Radar — AI for security and security for AI
git clone https://github.com/Neetx/ai-security-research-radar.git -
dokimi
SkillsDokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.
git clone https://github.com/intel/dokimi.git -
code-conductor
SkillsA governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.
git clone https://github.com/yeisonrestrepo/code-conductor.git -
ai-dev-kit
SkillsAgent skills (SKILL.md), layered coding standards, a project-wide code audit and optional free/local MCP servers for AI-assisted development: Claude Code, OpenCode, Codex and any agent that reads markdown.
git clone https://github.com/AftabIbrahimKazi/ai-dev-kit.git -
arsenal
SkillsPortable workflow skills and controlled runtime for Pi, OMP, Codex, and Claude Code
git clone https://github.com/mirkobozzetto/arsenal.git -
craft-your-textbook
Skills本项目是 Socratopia(破卷)生态的衍生项目,是其"造书"环节的方法论沉淀,已固化为一个可复用的 skill。 让你具备亲手为自己造一本教材的能力——把一本教材(或一个领域的知识)加工成 AI 老师能拿去上课的教学蓝本。有教师用书时,造出来的书还能直接针对应试(见第四节)。
git clone https://github.com/xx-hub/craft-your-textbook.git -
paranoid-qa
SkillsClaude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
git clone https://github.com/akovalion/paranoid-qa.git -
hook-everything
SkillsAI skills for human-sounding copy and ethical hooks, with a zero-dependency slop scanner.
git clone https://github.com/Vumb-VibeCoder/hook-everything.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.