Library
85,762 resources from 11 public sources. 54 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
-
agent-plugins-skills
SkillsAgentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.
git clone https://github.com/richfrem/agent-plugins-skills.git -
forge-skills
SkillsThe Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.
git clone https://github.com/atlassian/forge-skills.git -
researchforge
SkillsA lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).
git clone https://github.com/forger-labs-hq/researchforge.git -
MeowKit
SkillsProduction ready. AI Agent Workflow System for Claude Code
git clone https://github.com/ngocsangyem/MeowKit.git -
qa-skills
SkillsTesting skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Agent 的测试工程技能。
git clone https://github.com/fishzjp/qa-skills.git -
review-squad
SkillsDispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks
git clone https://github.com/2389-research/review-squad.git -
done-means-done
SkillsResumable completion protocol for coding agents: obligations live in a durable task record, completion is computed by a validator, and a Stop hook routes execution back to unfinished work.
git clone https://github.com/PyModel/done-means-done.git -
claude-qa-flow
SkillsQA workflow for AI coding agents: ticket → reviewed test plan → real-browser run with independent evidence review → bug tickets. Claude Code, OpenCode, any Agent Skills harness.
git clone https://github.com/QAMarcos/claude-qa-flow.git -
Gridline
SkillsPortable AI agent skills, subagents, and plugins for architecture/AEC workflows across Codex, Claude Code, Gemini CLI, and other compatible agents.
git clone https://github.com/MakeItEzzz555/Gridline.git -
mantle
SkillsClaude Code plugin: themes & 4K wallpapers for Claude Code, Windows Terminal, iTerm2 and claude.ai, a searchable index of 47,000+ agent skills, MCP servers and plugins, and a setup doctor for CLAUDE.md, MCP and context.
git clone https://github.com/AkshitTiwarii/mantle.git -
totally-integrated-claude
SkillsA Claude Code plugin for Siemens TIA Portal engineering automation.
git clone https://github.com/Czarnak/totally-integrated-claude.git -
trina-ax
SkillsSet up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.
git clone https://github.com/trina-app/trina-ax.git -
claude-code-eyes
SkillsGive Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before power-on, and catch bugs that live on the glass, not the logs.
git clone https://github.com/fcavalcantirj/claude-code-eyes.git -
CoalFace
SkillsFan-out discipline for AI coding agents - scout, partition, wave, QC, single-writer apply, receipt. Bounds a swarm to the solo-cost budget; does not make models smarter. Zero-dependency, Phoenix-13. Part of TheColliery.
git clone https://github.com/TheColliery/CoalFace.git -
PMM-Skills
SkillsOpen-source product marketing skills for Claude Code and Codex: research, positioning, messaging, GTM, launches, and competitive intelligence.
git clone https://github.com/mia-ppp/PMM-Skills.git -
trace-to-practice
SkillsEvidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.
git clone https://github.com/wssfk12138/trace-to-practice.git -
workinggenius
SkillsWork doesn't fail at random — it fails at whichever genius got skipped. The Six Working Geniuses (Wonder, Invention, Discernment, Galvanizing, Enablement, Tenacity) as Agent Skills for coding agents. Claude Code, Cursor, Codex & any SKILL.md client.
git clone https://github.com/donald-ada/workinggenius.git -
visual-stack
SkillsA visual interface for building software with Claude Code/Codex.
git clone https://github.com/Cavalry-Collective/visual-stack.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 -
agent-skills
SkillsOfficial agent skills for PowerSync
git clone https://github.com/powersync-ja/agent-skills.git -
gtm-eng-skills
Skills10 AI agent skills for Claude Code — waterfall email enrichment, TAM building, signal discovery, job change detection, and outbound automation. Powered by Deepline CLI with 28+ GTM data providers.
git clone https://github.com/getaero-io/gtm-eng-skills.git -
kasetto
Skills📼 Declarative AI agent environment manager, written in Rust
git clone https://github.com/pivoshenko/kasetto.git -
rig
SkillsCross Agent Dynamic Workflows as a Skill
git clone https://github.com/githubnext/rig.git -
MAJI-Skills
SkillsSkills for AI agents, built from real work: a working discipline plus playbooks for planning, shipping, documents, images, video and sales. Plain SKILL.md files for Claude Code, Cursor, Antigravity, Codex and Gemini CLI. AGPL v3.
git clone https://github.com/Ijam18/MAJI-Skills.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.