仓库/Skill 库

面向 Agent 工具的 OpenRouter。社区入口：https://discord.gg/6mQYYfFMAnOpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn

面向 AI 创作的开源无限画布工作台，集成 AI 生图、参考图编辑、视频生成、Agent 智能助手、画布编排、对话创作、提示词库与素材管理等能力，支持可视化创作流程与多 Agent 协同工作。兼容 OpenAI 接口生态，支持 chatgpt2api、grok2api、flow2api、newapi 等渠道接入。

人与 Agent 协同构建。Where people and agents build in tune.

面向科学研究场景的开源 AI 工作台。The open-source AI workbench for scientific research

与一个 Agent 对话，派出一支团队交付Talk to one agent. Ship with a crew.

汇聚每个 Agent 的模型，一站式管理。从菜单栏即可使用 DeepSeek 上的 Codex、Kimi 上的 Claude Code。Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

基于 Three.js 构建的使命召唤品质级 FPS 游戏，仅由一条 prompt 生成。A Call of Duty-quality FPS in Three.js, built from a single prompt.

将 Claude Design 作为 Agent Skill 本地运行——支持 Cursor、Claude Code 等。在 claude.ai/design 之外，生成可直接交付的 HTML 形式精致 UI mockup、原型、演示稿和线框图。最佳搭配 Opus 4.8。Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus 4.8.

把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

一个实用的 AI agent 循环库，并提供可安装的 skill，用于查找、改写和设计可复用的 agent 工作流。A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

专为复杂代码库打造的 Agent harness，在 Codex 内提供项目记忆、规划、执行与验证闭环。The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

Goose Swift 概念验证 README。Goose Swift proof-of-concept README

Agent 团队的聚集地。跨平台团队聊天工具，AI Agent 作为一等队友 — 支持云端大脑或自带大脑（Claude Code / Codex）。Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

给云端 AI agents 提供运行在你自有机器上的真实开发环境。Give cloud AI agents a real development environment on your own machines.

全球首个开源的企业级世界模型。World's first open-source enterprise world model.

开源自托管的 AI 漏洞研究工具，通过编排 Agent 发现并验证代码中的安全问题。Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

异步优先的 agent harness。Async-first agent harness

通用去 AI 化写作 Skill，兼容任意 Agent Skills 协议的 Agent（通过 Skills CLI 支持 77+），并提供 Claude Code、Codex、Grok Build、Antigravity 的原生插件。修复虚构写作的叙事架构，按场景匹配专业文体规则。基于 StoryScope（arXiv:2604.03136）。De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).

下一代源码可用的 Codex 与 Claude Code 替代品——一个本地优先、可自托管的 Agent 工作空间，覆盖代码、办公文档、可编辑设计、演示文稿、网站与视频。用 AI 构建后，可像 PowerPoint 一样轻松编辑文字、图片、配色、布局与场景。Next-gen, source-available alternative to Codex and Claude Code — one local-first, self-hostable agent workspace for code, office work, editable design, presentations, websites, and video. Build with AI, then edit text, images, colors, layouts, and scenes as easily as PowerPoint.

Grok Bot 的开源替代方案，提供 bot 可调用的虚拟机。Open Source Alternative to Grok Bot with a virtual machine that bots can use

开源、local-first 的桌面端 AI 研究工作台，面向 Python/R 科学计算，集成 MCP 生信工具、SSH/WSL/GPU runtime，以及 OpenAI/Anthropic 模型。Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.

将 Agent 构建的产品正式上线：托管、数据库、域名、邮件、支付——全部使用你自己的账号。开源 Agent Skill + 零依赖 Node CLI：detect → plan → approve → apply → verify。无需 GoLive 账号、后端或遥测。Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, backend or telemetry.

阻止你的 AI 胡编乱造——AI 提出方案，确定性工具做决策，每条断言都对照真实证据进行核验。可信事实与上下文在重置后仍能保留。逆向工程作为验证场。MCP server + CLI。Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

🧩 FrontierAgent，我们的 agent 框架，与之同步开源——原生命令行 TUI，支持 ReAct 与 Agent Team 模式，macOS 与 Linux 上一条命令即可运行，无需预装，无强 Docker 依赖。🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese

去除论文和基金申请书（NSF/NIH）中的 AI 写作痕迹，同时保留学术语气并将主张与证据挂钩。适用于 Claude Code、Codex 和 MorphMind 的 Skill。Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.

开源桌面 AI agent，涵盖工具、文件、知识、工作流与真实交付物。Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

一个激活 Fable 风格 Agentic 行为的 Claude skill：显式多阶段规划、子 Agent 委派和自我验证。A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.

一个经过验证、社区维护的目录，涵盖 896 个使用 Jev 构建的开源项目。A verified, community-maintained catalog of 896 open-source projects built with Jev.

AI 短剧制作的 skill 集合：拆角色、出设定图、排大纲 | Agent skills for AI short-drama production — character bibles, model sheets, adaptation outlines. Runs in Claude Code & codex.

为 AI Agent 提供 fetch、搜索和爬取功能。使用 Rust 从零构建，无需密钥，无需账号。AGPL v3 许可。Web fetch, search, and crawl for AI agents. Built from scratch in Rust. No keys, no accounts. AGPL v3.

Claude skill：将任何流程、想法或问题设计成 ICM 工作空间（以文件夹结构作为 Agent 架构），或将现有文件夹重构为该结构Claude skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one