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
-
从游戏客户端反推服务端协议并复现可部署服务端 (Agent Skill)。Unity/UE/Cocos, IL2CPP/Lua/JS…
git clone https://github.com/ShrugYu/game-client-to-server-reverse.git -
agent-distro
SkillsYour team's coding agents, in one command (powered by Nix)
git clone https://github.com/juspay/agent-distro.git -
QAMap
SkillsLocal pull-request review brief for coding agents: the diff, the tests and callers of changed code, and change signals in one report. No LLM call, no upload. Claude Code used 44% fewer tokens with it on 42 public PRs.
git clone https://github.com/IvoryCanvas/QAMap.git -
story-skills
SkillsAgent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.
git clone https://github.com/danjdewhurst/story-skills.git -
stack-diagram
SkillsAgent skill: describe your stack in a sentence, get an architecture diagram with official logos
git clone https://github.com/caru-ini/stack-diagram.git -
cc-settings
Tools & appsClaude Code configuration — agents, skills, hooks & settings for Darkroom Engineering
git clone https://github.com/darkroomengineering/cc-settings.git -
SWE-agent
Tools & appsSWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
git clone https://github.com/SWE-agent/SWE-agent.git -
nopua
Prompts一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不再撒谎,找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.
git clone https://github.com/wuji-labs/nopua.git -
superdesign-prompts
Prompts128 usage-ranked, vision-curated UI design prompts (full design specs + live previews) that stop your AI coding agent from shipping generic AI-slop UI. Powered by superdesign.dev
git clone https://github.com/superdesigndev/superdesign-prompts.git -
Sage-A1.5-Q4_K_M-GGUF
Modelstext generation model by InternScience · gguf
InternScience/Sage-A1.5-Q4_K_M-GGUF -
Poracode
Tools & appsOne window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and chat, any layout.
git clone https://github.com/Porabuild/Poracode.git -
ccprompts
Promptspractical claude code commands and subagents
git clone https://github.com/ursisterbtw/ccprompts.git -
agent-stash
SkillsPersonal Agent Skills and DeepSeek Harness (DSH) plugins: message edit, Skill Scout, prompt recall, autosuggest and enhance, plus a DSH plugin index. /init for Pi, DSH, Cline, Grok Build, goose and Aider, with presets from Claude Code, Codex, OpenCode, Crush, Qwen Code, Kilo Code, Kimi Code and Copilot CLI.
git clone https://github.com/Alice39s/agent-stash.git -
Hail_Hydra
Agents & frameworks🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.
git clone https://github.com/AR6420/Hail_Hydra.git -
agent-skills
SkillsCashfree Agent Skills
git clone https://github.com/cashfree/agent-skills.git -
itr-wala
SkillsFile your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-27. Claude Code / Codex / Gemini skill.
git clone https://github.com/karanb192/itr-wala.git -
sugar
Agents & frameworksMission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.
git clone https://github.com/roboticforce/sugar.git -
avibe
Agents & frameworksMake your computer a home for your AI partner. Avibe is the local-first Agent OS, with desktop apps for Mac and Windows, an iPhone app, and a command line for Linux. Vibey, its built-in AI partner, works out of the box, and developers can run Claude Code, Codex and OpenCode unchanged beside it.
git clone https://github.com/avibe-bot/avibe.git -
capri-ai-desktop
Agents & frameworksCapri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.
git clone https://github.com/edgerunners-2/capri-ai-desktop.git -
paad
SkillsThe practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.
git clone https://github.com/Ovid/paad.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
cesiumjs-skills
SkillsCurated agent skills for CesiumJS development.
git clone https://github.com/CesiumGS/cesiumjs-skills.git -
Adnify
Agents & frameworksA local‑first AI Agent IDE that plans, edits, debugs and ships projects. Your clever otter‑flavored coding teammate.🦦
git clone https://github.com/ad-naan/Adnify.git -
zat.env
SkillsVerification-first agentic coding harness for Claude Code.
git clone https://github.com/peterzat/zat.env.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.