Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
neo-agent-skills
SkillsThe working rules (skills) the cross-model Neo.mjs agent team loads every session: ticket intake, PR review gates, lane coordination and guards, versioned as one package. For apps built on Neo.mjs, for contributors, and for anyone who wants to read them.
git clone https://github.com/neomjs/neo-agent-skills.git -
doki
SkillsAI second brain vault for Obsidian — an agent compiles web clippings into a cited Markdown wiki. Claude Code + Git, model-neutral. 옵시디언 기반 AI 지식관리(PKM) 템플릿
git clone https://github.com/lemoncloud-io/doki.git -
the-agency
SkillsClaude Code, fixed for everyone. Memory that survives sessions, agents that finish what they start, QA gates before 'done', the right model for each job. 235+ skills. Installs to ~/.claude/ — no cloud, no extra keys.
git clone https://github.com/Tekkiiiii/the-agency.git -
maw
SkillsAdversarial multi-agent pipeline for Claude Code and Codex CLI: planning, plan review, implementation, cross-model code review, QA. Installable skills, no runtime.
git clone https://github.com/pockerhead/maw.git -
icode-skill
SkillsAI coding workflow for Claude Code, Codex and CodeBuddy: ticket-based development, resumable steps, evidence-based verification and independent multi-model review. AI 编码工作流:工单管理、断点续接、证据化验证、跨模型设计与代码复评。
git clone https://github.com/ayukyo/icode-skill.git -
awesome-vibe-coding-websites
SkillsVibe coding website templates: 270+ original websites and 550+ live demos built by AI coding agents (Claude, GPT, Gemini, Grok, Kimi, GLM, DeepSeek). Each has the exact prompt and DESIGN.md — paste into Claude Code, Cursor or Codex to build landing pages, SaaS sites, portfolios, stores, dashboards and 3D games. Updated with every new model.
git clone https://github.com/liyupi/awesome-vibe-coding-websites.git -
devcycle
SkillsTurns a short feature/bug description into a reviewed, on-device-verified implementation — parallel subagents, cross-model review, GitHub reconcile, and a doctor/learn loop that benchmarks and improves the pipeline itself. Built on superpowers.
git clone https://github.com/KonstantinRoehrl/devcycle.git -
skill3
SkillsSkill3 is a lightweight Java CLI that relearns a technical skill for an AI agent. It discovers documentation sources, scores them for authority and freshness (anchored to a target model's knowledge cutoff), synthesizes them with a local LLM into an Agent Skills SKILL.md, and vets the result with NVIDIA's SkillSpector.
git clone https://github.com/PIsberg/skill3.git -
openai-docs
SkillsUse when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
$skill-installer <skill-name> -
openai-docs
SkillsUse when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
$skill-installer <skill-name> -
rumo-engineering-skills
Skills面向 Claude Code、Codex 等 AI 编程 agent 的工程技能:澄清需求、计划、调试、测试验证、代码评审,改数据库、删文件、动服务器前的确认与回滚,以及跨 agent 派活和多模型评审。Engineering skills for Claude Code, Codex, and other coding agents: clarify, plan, debug, verify, and review; approval and rollback before database, file, or server changes; delegation and multi-model review across agents.
git clone https://github.com/rumoii/rumo-engineering-skills.git -
hermes-jailbench
SkillsZero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
git clone https://github.com/hermes-labs-ai/hermes-jailbench.git -
boss-skill
SkillsPlugin for Claude Code: sends each coding task to the cheapest model that can do it right, keeps your main chat lean, reviews every diff. Debates, plus Codex, Gemini, Kimi, Qwen or Ollama as second opinions.
git clone https://github.com/mefayed/boss-skill.git -
prototype
SkillsBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
-
mcp-builder
SkillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
/plugin marketplace add anthropics/skills -
writing-skills
SkillsClaude Code skills for rewriting AI-drafted prose to pass AI detectors: a measured three-step pipeline (structural rewrite, tell removal, cross-model diction) scored against Pangram, plus reference management and citation auditing.
git clone https://github.com/petar-djukic/writing-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.