Library
85,340 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
-
awesome-copilot-studio-agents
Prompts103 paste-ready declarative agents for Microsoft 365 Copilot. No coding. No Azure. Deploy in minutes.
git clone https://github.com/kesslernity/awesome-copilot-studio-agents.git -
AIGuide
PromptsAI 应用开发、AI 编程实战与面试指南,涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。
git clone https://github.com/Snailclimb/AIGuide.git -
Semantic-Anchors
PromptsA curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.
git clone https://github.com/LLM-Coding/Semantic-Anchors.git -
mantis
PromptsA modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
git clone https://github.com/google/mantis.git -
awesome-ai-agent-tools
PromptsAI agent tools for coding assistants: skills, MCP servers, agent loops, subagents, hooks, plugins, and CLI tools. Machine-readable catalogs. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.
git clone https://github.com/michielhdoteth/awesome-ai-agent-tools.git -
maestro
PromptsWorkflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.
git clone https://github.com/sharpdeveye/maestro.git -
agent-skills
PromptsA collection of AI agent skills for Clawdbot, Claude Code, Codex
git clone https://github.com/jdrhyne/agent-skills.git -
rsc-harness
PromptsYour agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.
git clone https://github.com/ericrisco/rsc-harness.git -
OJO-Design-Skills
PromptsReusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.
git clone https://github.com/touchine-ojo/OJO-Design-Skills.git -
product-mode
PromptsThe most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.
git clone https://github.com/sohaibt/product-mode.git -
mattpocock-skills-zh-CN
PromptsMatt Pocock skills 的简体中文本地化:人工审核每一次更新,定期同步上游,支持 Claude、Codex 和 DSH 插件。
git clone https://github.com/vinvcn/mattpocock-skills-zh-CN.git -
meta-llm-charter
PromptsCompact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.
git clone https://github.com/entropyvortex/meta-llm-charter.git -
vibes-plug
PromptsUniversal AI Agent Swarm & MCP Plugin with 178 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf, and OpenAI Codex.
git clone https://github.com/roedyrustam/vibes-plug.git -
grim-prompter
PromptsThreat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
git clone https://github.com/jmanico/grim-prompter.git -
spec_driven_develop
PromptsSpec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.
git clone https://github.com/zhu1090093659/spec_driven_develop.git -
chinese-novelist-skill
Prompts🎭 AI 写小说:从零生成 10-50 章完整中文小说,三层问答 · 创作记忆 · 悬念钩子 · 自动校验,长篇网文连载皆宜|开源免费,适配主流 coding agent|🤝 Infistar.cc 赞助 · 注册送 $5|AI novel writing skill
git clone https://github.com/PenglongHuang/chinese-novelist-skill.git -
moneyhelper
PromptsAuditable AI finance department: enterprise tenants, double-entry GL, expenses, procurement/payables, bank reconciliation + personal ledger, portfolio and CN tax. Numbers come from deterministic code, never the model.
git clone https://github.com/badhope/moneyhelper.git -
awesome-goal-prompts
PromptsSource-backed /goal contracts for Claude Code, Codex and Cursor, with a searchable catalog and separate reusable seed patterns.
git clone https://github.com/majiayu000/awesome-goal-prompts.git -
designer-skills
PromptsDesigner Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.
git clone https://github.com/Owl-Listener/designer-skills.git -
ring
Prompts89 skills and 38 specialized agents that enforce proven engineering practices for AI-assisted development. TDD, systematic debugging, parallel code review, and 10-gate development cycles — as a Claude Code plugin marketplace.
git clone https://github.com/LerianStudio/ring.git -
honey-for-devs
PromptsHoney (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
git clone https://github.com/Green-PT/honey-for-devs.git -
awesome-agentic-ai
PromptsAgentic AI knowledge hub: 408 Cursor/Claude/Codex skills, 108 papers, 201 ML notebooks, 9 textbooks, 112 curated repos, 5,380 OpenClaw skills. Vendored skills + link-only catalogs. Start at AGENTS.md.
git clone https://github.com/adriannoes/awesome-agentic-ai.git -
sun-style-writing
Prompts从孙割19年白月光的痛彻心扉中蒸馏出来的无上心法
git clone https://github.com/KKKKhazix/sun-style-writing.git -
agent-style
Prompts21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.
git clone https://github.com/yzhao062/agent-style.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.