Library
86,689 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
-
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 -
oh-my-diff
SkillsOh My Diff: A Moddable Codex Runtime
git clone https://github.com/dzkchen/oh-my-diff.git -
skills
SkillsAgent Skills to help developers using AI agents with Lingui
git clone https://github.com/lingui/skills.git -
rigorkit
SkillsTool-neutral skills and workflows for rigorous AI-assisted development.
git clone https://github.com/harrypotter48/rigorkit.git -
AI-Code-Tutorials
PromptsBilingual AI coding tutorials for Claude Code and OpenAI Codex: setup, CLI, Codex workflows, MCP, agents, code review, prompt engineering, and web projects.
git clone https://github.com/0xfnzero/AI-Code-Tutorials.git -
cloudterm
SkillsAI powered SSH, SFTP, telnet and Windows RDP in a single window, with integrations for Claude Code, Codex and OpenCode agent that reads and execute commands in the session in front of you. Free and open source.
git clone https://github.com/BradPerbs/cloudterm.git -
awesome-chinese-ai-tools
Skills中文 Agent Skills 合集:212 个条目、13 个本站原创;Codex 13/13 自动触发实测,Claude Code 部分实测 · Cursor 待测;来源仓库定期复检,运行记录公开
git clone https://github.com/sanhuang520-ship-it/awesome-chinese-ai-tools.git -
stacklit
MCP serversStop making your AI re-read your codebase. Stacklit maps your repo once and keeps the map fresh. In a 450-session test, agents ran 82% fewer grep and glob searches. Free, MIT, one Go binary. Sets up Claude Code, Cursor, Codex and 22 more.
git clone https://github.com/glincker/stacklit.git -
nuguard
MCP serversAI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
git clone https://github.com/NuGuardAI/nuguard.git -
open-bridge
SkillsStop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot CLI. MIT.
git clone https://github.com/bks-lab/open-bridge.git -
forward-deployed-selling
PromptsForward Deployed Selling: the enterprise sales doctrine for the AI era, as a Claude Code plugin. Thirteen /fds commands, enforcing hooks, reviewing agents, typed records, evals.
git clone https://github.com/vonarmen-wq/forward-deployed-selling.git -
human-review
SkillsA /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.
git clone https://github.com/victorrentea/human-review.git -
retro-design-system
Prompts53 retro HTML/CSS UI themes for AI-assisted frontend development. Windows 95, CRT, vaporwave, DOS, arcade, mainframe, and more.
git clone https://github.com/NovusGFX/retro-design-system.git -
plombir-git
MCP serversLightweight, open-source, self-hosted Git server and forge written in Rust. Gitea/Forgejo/GitHub alternative with pull requests, CI/CD and built-in MCP for AI agents.
git clone https://github.com/Nettechnologys/plombir-git.git -
agent-collab-skills
SkillsClaude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
git clone https://github.com/WenyuChiou/agent-collab-skills.git -
Hybrid-Computer-Use
Agents & frameworksOfficial code for "Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents"
git clone https://github.com/microsoft/Hybrid-Computer-Use.git -
Skill-hub
SkillsReusable AI agent skills for Codex, Claude Code etc. — AI coding workflows, SKILL.md templates, and automation practices. 面向 Codex、Claude Code等agents 的可复用 AI Agent Skill 技能库:AI 编程工作流、SKILL.md 模板与自动化实践。
git clone https://github.com/EthanYoQ/Skill-hub.git -
agent-ready-repo
SkillsThe complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.
git clone https://github.com/eugenelim/agent-ready-repo.git -
unified-code-review
SkillsRisk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.
git clone https://github.com/dancingteeth/unified-code-review.git -
ginno
SkillsLocal-first personal AI agent desktop app — Claude Code's shape with a visual workflow studio, local knowledge base, and zero cloud. Tauri + Next.js + Python.
git clone https://github.com/robscc/ginno.git -
llmslim
MCP serversLong-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
git clone https://github.com/Thanatos9404/llmslim.git -
apkscope
MCP serversAndroid reverse engineering for humans and AI agents: typed Java in milliseconds, xrefs, API and secret recon, APK diff, re-signing, a native viewer and an MCP server. One Rust executable, no JVM.
git clone https://github.com/suffixing/apkscope.git -
buddy
Tools & appsA virtual pet companion for your AI — Designed to provide in-context code review feedback with personality. Grow with your buddy and level up together. Works with Claude Code, Codex, CursorCLI, Github CopilotCLI, OpenClaw, and any MCP compatible clients
git clone https://github.com/fiorastudio/buddy.git -
knowhow
SkillsInstall and manage AI agent skills from any git repo (npx skills compatible) for Claude Code, Codex, OpenCode, Gemini and more
git clone https://github.com/jkitchin/knowhow.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.