Library
86,235 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-guard
SkillsScan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.
git clone https://github.com/elliottwaves-20/agent-guard.git -
cc-foundry
SkillsClaude Code plugins its author uses every day: coding, commit, planning, and writing discipline, plus Go, JavaScript/TypeScript, PHP, Python, Rust, frontend, backend, Grafana, CLI, and infrastructure skills.
git clone https://github.com/xobotyi/cc-foundry.git -
skills
SkillsFree Claude Code skills for UI design: typography, layout and spacing, and UX writing. Also works in Codex, Cursor and other AI coding agents.
git clone https://github.com/wensity/skills.git -
Comprehensive YouTube channel analysis: researches background, creates data visualizations, and generates execution plans.
git clone https://github.com/alphaparkinc/openclaw-genpark-channel-auditor.git -
jump-skills
SkillsJump Skill Ninjas are intelligent meta-skills — master orchestrators that route your requests to the most appropriate specialized skill from a curated library. Instead of manually searching through hundreds of individual skills, you simply describe your task and the Ninja Identifies specialized skills and Loads the full skill in context
git clone https://github.com/fabricioctelles/jump-skills.git -
megapowers
SkillsOne plugin for Claude Code and Codex: task skills, an output style, a destructive-command tripwire, and a doctor. Measured, not vibed.
git clone https://github.com/lawzava/megapowers.git -
crypto-defi-skills
Skills81 installable DeFi skills in 17 independent packs for Claude Code, Codex, Cursor, Gemini CLI, Hermes and OpenClaw. Protocol reads, risk checks, unsigned plans and settlement evidence.
git clone https://github.com/galleonlabs/crypto-defi-skills.git -
Upkeep
SkillsUpkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.
git clone https://github.com/wei18/Upkeep.git -
semantic-markdown
SkillsSemantic Markdown (.smd): Markdown for developers, PMs and AI agents — callouts, colors, diagrams, decisions, risks, APIs, KPIs. VS Code extension, CLI and agent skills with token-efficient agent views.
git clone https://github.com/bislink360/semantic-markdown.git -
evergreen-codex-skills
SkillsEvergreen, generally useful Codex skills designed to stay valuable as models improve.
git clone https://github.com/Kbediako/evergreen-codex-skills.git -
zat.env
SkillsVerification-first agentic coding harness for Claude Code.
git clone https://github.com/peterzat/zat.env.git -
pm-superpowers
SkillsFind your product's moat in minutes. Product strategy skills (moats, VRIO, pre-mortem) for Claude Code and Cursor.
git clone https://github.com/aniganti/pm-superpowers.git -
reference-to-game
SkillsInput-agnostic reference-to-game skill: preserve style and colors while building playable games. Includes tools, fal asset workflows and four Three.js examples.
git clone https://github.com/gokayfem/reference-to-game.git -
shellflow
Skillsshellflow is a shell-native, agentless automation tool that runs commands over ssh - concurrently, idempotently and 10x faster than ansible.
git clone https://github.com/longcipher/shellflow.git -
linear-claude-skill
SkillsAgent skill for managing Linear issues, projects, and teams. MCP tools, SDK automation, GraphQL API patterns.
git clone https://github.com/wrsmith108/linear-claude-skill.git -
livewire-alpine-skills
SkillsAgent Skills for Laravel Livewire v4 + Alpine.js v3. Recipes EXECUTED against a real install (14 tests), a 21-rule reviewer that gates on exit code, project-convention detection, and an objective eval. 12k lines from the official docs.
git clone https://github.com/olgunozoktas/livewire-alpine-skills.git -
openapi
SkillsPachca API platform: MCP server and plugin for AI agents (Claude Code, Codex, VS Code, Cursor) with skills and commands, OpenAPI spec, CLI, SDKs (TypeScript, Python, Go, Kotlin, Swift, C#) and n8n node
git clone https://github.com/pachca/openapi.git -
skills
SkillsClaude Code skills for querying Coinpaprika and DexPaprika crypto market data (CEX prices, DEX pools, tokens, OHLCV).
git clone https://github.com/coinpaprika/skills.git -
WongStack
SkillsRepo-native workflow for AI coding agents: your team's process, plans, and decisions live in the repo, so Claude Code and Codex run the same explore → plan → apply → ship loop.
git clone https://github.com/matthewwong525/WongStack.git -
mockbird
SkillsFour Agent Skills that stop AI agents from shipping generic UI: a screen canvas with real interactive HTML mockups, per-project design system, validator and a self-updating OpenCode v2 plugin.
git clone https://github.com/misereitor/mockbird.git -
Automatically filters and aggregates AI news, extracts article data, and produces actionable commercial intelligence.
git clone https://github.com/alphaparkinc/openclaw-genpark-signal-aggregator.git -
google-play-cli-skills
SkillsAgent skills (SKILL.md) for the gplay Google Play CLI — install via: npx skills add PollyGlot/google-play-cli-skills
git clone https://github.com/PollyGlot/google-play-cli-skills.git -
genpark-node-manager
SkillsA sophisticated UI for managing clusters of high-frequency OpenClaw/GenPark nodes.
git clone https://github.com/Alpha-Park/genpark-node-manager.git -
leverage
SkillsAgents are the newest form of leverage. Skills + blueprints that give yours something real to work with: live social data, people + company enrichment, a workspace Postgres, schedules, shareable dashboards. Solo founder, big company, day job, or your personal life: one install, any agent.
git clone https://github.com/superagnt/leverage.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.