Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
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 -
Agent-App
SkillsAgent App is application that AI agent can build, evolve, and operate. A collaboration space for both humans and agents.
git clone https://github.com/CraftOS-dev/Agent-App.git -
tg_content_factory
SkillsTelegram automation for coding agents — Claude Code plugin + tg-agent CLI. Read/send messages, manage channels, media, analytics, content pipelines. Multi-account, flood-safe, Telethon-powered.
git clone https://github.com/axisrow/tg_content_factory.git -
16 Claude Code skills for data engineers: profile a new source, investigate a failed run, review a change, document the platform. Most end in a page you can share.
git clone https://github.com/DataWithBaraa/claude-code-data-engineering-skills.git -
brigade
SkillsBrigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP and skills sync for Claude Code, Codex, Cursor, OpenCode, and T3 Code.
git clone https://github.com/escoffier-labs/brigade.git -
a-fable-of-codexes
SkillsClaude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.
git clone https://github.com/jvogan/a-fable-of-codexes.git -
vigilante
SkillsVigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.
git clone https://github.com/aliengiraffe/vigilante.git -
model-citizen
SkillsThe control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.
git clone https://github.com/JakeSelby/model-citizen.git -
hashtree
SkillsPermissionless storage and Git for humans and agents. Publish and clone with local keys—no hosting account.
git clone https://github.com/mmalmi/hashtree.git -
rudder-agent-skills
SkillsClaude Code plugin marketplace & agent skills for RudderStack — instrument events, design tracking plans & data graphs, write transformations, build Profiles, and drive the CLI, MCP server, and Terraform provider from Claude Code, Cursor, and 40+ AI agents.
git clone https://github.com/rudderlabs/rudder-agent-skills.git -
github-project-skill
SkillsAgent Skill for GitHub repository setup and platform-specific features | Claude Code compatible
git clone https://github.com/netresearch/github-project-skill.git -
ARIS-Movie-Director
SkillsAgentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.
git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git -
skills
SkillsOpen-source marketing skills that turn Claude Code, Codex and other AI agents into an AI CMO.
git clone https://github.com/Ekos-Labs/skills.git -
ai-research-radar
SkillsAI Research Radar — Evidence-Grounded Trend Ledger for AI Systems
git clone https://github.com/Neetx/ai-research-radar.git -
crux
SkillsA scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.
git clone https://github.com/mehdiforoozandeh/crux.git -
network-reuse-protocol
SkillsA portable AI work protocol: reuse proven solutions, limit redundant retrieval, deliver results. 让 AI 先复用、少重复、重交付。
git clone https://github.com/RenatusPang/network-reuse-protocol.git -
Agent Skill for systematically upgrading TYPO3 extensions to newer LTS versions | Claude Code compatible
git clone https://github.com/netresearch/typo3-extension-upgrade-skill.git -
skills
Skills29 Claude Code skills, 4 subagents and 3 hooks: grilling, handoffs, a kanban workflow, an unattended orchestrator with a merge gate, multi-account /switch and reminders. Install one skill or a whole workflow. MIT.
git clone https://github.com/KrishP147/skills.git -
done-is-a-claim
SkillsYour coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.
git clone https://github.com/Grit-77/done-is-a-claim.git -
dely
SkillsMulti-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca supervision for Claude Code, Codex, Cursor, Antigravity, and other AI coding agents.
git clone https://github.com/hieuphung97/dely.git -
pronounce
Skills🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP + Agent Skill.
git clone https://github.com/anzy-renlab-ai/pronounce.git -
Bossku-Superpowers
SkillsMake your AI coding agent work properly: pick the right skill, run its own code, and remember your project rules.
git clone https://github.com/wankimmy/Bossku-Superpowers.git -
guizang-game-skill
Skills歸藏 Game Skill:让 AI 从零做出能在浏览器里玩的 3D 动作游戏,附可玩演示《雾锁山门》。Agent skill for Claude Code / Codex that builds a playable browser 3D action game with AI-generated assets (three.js, single-HTML). Playable demo included.
git clone https://github.com/op7418/guizang-game-skill.git -
somtum
SkillsLong-term memory for Claude Code and Codex that meters every token it spends
git clone https://github.com/riz007/somtum.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.