Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
curated-claude-code
SkillsA small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
git clone https://github.com/Sanexxxx777/curated-claude-code.git -
textbook-writer-skills
SkillsUbD 逆向设计驱动的教材写作 skill 组合,一键装进 Claude Code / Codex / WorkBuddy:教学定位 → 五件套 gate → 章节树 gate → 四段式逐章写作 → 审核定稿。学科无关内核 + 可插拔学科档案,理科真算复核、人文社科逐字核对引文出处,验证不了就标注「需作者确认」;关键决策作者拍板,中断随时续写
git clone https://github.com/cabbage2000-lab/textbook-writer-skills.git -
trinity-claw
SkillsA self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.
git clone https://github.com/TrinityClaw/trinity-claw.git -
roost
SkillsSpec-driven development that doesn't stop at the code: coding agents take an idea to release, and you make the calls.
git clone https://github.com/Beakpoint-Insights/roost.git -
swarmstorm
SkillsMulti-agent orchestration for Claude Code, Codex and Cursor: parallel coding agents that settle shared files before the merge, QA agents that test the running app, clickable prototypes, workbenches and live plans in aiview. Your own subscription. MIT.
git clone https://github.com/Ovich/swarmstorm.git -
aiteamkit
SkillsMulti-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard, handover. Author and approver stay separate roles.
git clone https://github.com/lamngockhuong/aiteamkit.git -
tiktok-video-skills
SkillsShort-form video skills for Claude Code — engineer Reels, TikToks, and YouTube Shorts that survive the swipe.
git clone https://github.com/iart-ai/tiktok-video-skills.git -
rymac-4r-icm-audit
SkillsThe 4R audit for ICM folder systems: Read, Run, Reality, Report. A Claude Code skill that proves your AI workspace works, not just that it looks right.
git clone https://github.com/oathdriven/rymac-4r-icm-audit.git -
apple-dev-skills
SkillsSkills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
git clone https://github.com/wei18/apple-dev-skills.git -
jason-ai
SkillsJason AI: an AI SDR harness. The runtime's source, the skills, plugins, contracts, install path and releases.
git clone https://github.com/reply-team/jason-ai.git -
opentai.github.io
SkillsThe official website of the Open Trustworthy AI Community (OpenTAI).
git clone https://github.com/OpenTAI/opentai.github.io.git -
CoalMine
SkillsNine quality-canary skills for AI coding agents - code health, world-class rule completeness, grounding, supply chain, resilience, drift & more - plus the auto-cadence hooks that run them unprompted at session start and session end. Cross-agent, consent-gated, token-lean.
git clone https://github.com/TheColliery/CoalMine.git -
agent-eval-loop
SkillsBuild evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents
git clone https://github.com/relai-ai/agent-eval-loop.git -
mcp-socialmedia
SkillsMCP server that lets AI agents read and create posts, replies, and team-based discussions.
git clone https://github.com/2389-research/mcp-socialmedia.git -
atlasclaw-providers
Skillsatlasclaw-providers are the integration with enterprise systems through skills and webhook.
git clone https://github.com/CloudChef/atlasclaw-providers.git -
skill-router
SkillsSkill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.
git clone https://github.com/hussi9/skill-router.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 -
MemoryCustodian
SkillsDurable, repo-native project memory for coding agents, without context bloat.
git clone https://github.com/waittim/MemoryCustodian.git -
simmer
SkillsIterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements
git clone https://github.com/2389-research/simmer.git -
pixellab-pip
SkillsMeet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and animate pixel assets, then sniffs out a bigger prompt, scouts for a useful tool, and carries back what happened.
git clone https://github.com/Shilo/pixellab-pip.git -
seo-geo-optimizer
SkillsUniversal SEO & GEO skill for AI coding agents: Claude Code, Cursor, Windsurf, GitHub Copilot, Replit, Lovable, Bolt. Optimizes sites for Google, Bing, AI Overviews, ChatGPT and Perplexity.
git clone https://github.com/Aryanpanwar10005/seo-geo-optimizer.git -
Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。
git clone https://github.com/KarmenLoop/user-behavior-personalization.git -
industrial-aiops
SkillsVendor-neutral industrial data collection and cross-protocol diagnostics for AI agents and CLI: OPC UA, Modbus, S7, MQTT/Sparkplug B, BACnet and more. Evidence-based downtime investigation, alarms, data quality and OEE, with shared audit and governance. No model required for analysis.
git clone https://github.com/industrial-aiops/industrial-aiops.git -
arcgram
SkillsArcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)
git clone https://github.com/jovesun-lab/arcgram.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.