仓库/Skill 库

为 DeepSeek Harness 桌面版提供一流的 Linux 打包——通过原生 CI 构建，覆盖 x64/arm64 的 AppImage、.deb、.tar.gz。First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.

高性能视频生成网关与会话协调器。High-performance video generation gateway and session coordinator

交互式标注/分割的文献综述Literature Review for Interactive annotation/segmentation

视觉定位的文献综述Literature review of visual localization.

在 Swift、Objective-C++ 和 C++ 中解析并调用原生 API，无需手写 mangled name 或手动 ABI 转换。Resolve and invoke native APIs from Swift, Objective-C++, and C++ without writing mangled names or manual ABI casts.

ComfyUI 中的官方 MiniMax-H3 8 步 PDD Acc LoRA（alibaba-pai）：LoRA + 并行解码头库，基于已训练 sigmas 的 euler 调度，8 步生成音视频Official MiniMax-H3 8-step PDD Acc LoRAs (alibaba-pai) in ComfyUI: LoRA + parallel-decoding head bank, euler on trained sigmas, audio+video in 8 steps

PokePlus 2026：PokeMMO 冒险智能自动捕捉与对战机器人PokePlus 2026: Smart Auto-Catch & Battle Bot for PokeMMO Adventures

[ISPRS 2024] 卫星视频单目标跟踪：系统综述与定向目标跟踪基准[ISPRS 2024] Satellite Video Single Object Tracking: A Systematic Review and An Oriented Object Tracking Benchmark

多模态具身 Agent 综述：从电脑操作到机器人操作。Survey on Multimodal Embodied Agents: From Computer-Use to Robot-Use

VisionFoundry：使用合成图像教会 VLM 视觉感知。VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

受 Discord、Telegram 和 Zoom 启发的开源团队聊天和视频会议工具。OpenSource team chats and video conferences inspired with Discord, Telegram & Zoom

一个开源、agent-native 的多模态 AI 生成平台，基于 DeepSeek Harness 构建。每次交互都存在于 agent 对话与无限画布中，统一了创作、生成与编辑。An open-source, agent-native platform for multimodal AI generation, built on DeepSeek Harness. Every interaction lives in agent conversations and an infinite canvas, unifying creation, generation, and editing.

一款把任意图片转换为专业生图提示词的 Chrome / Edge 浏览器插件。支持网页右键识图、本地上传与剪贴板粘贴，生成中文、英文和 JSON 提示词，并提供历史记录与收藏。

面向 WordPress 的 SEO 内容创作与 Humanizer 工具，基于 OpenAI、Anthropic Claude 和 Gemini，支持可编辑 prompt、图片与 Opace AI Hub。SEO content creator and Humanizer for WordPress using OpenAI, Anthropic Claude and Gemini, with editable prompts, images and Opace AI Hub.

描述或绘制即可成真——Kiln 让 3D 打印走进现实。开源 MCP server：AI agent（Claude、Codex、Cursor 或任意 MCP client）可在 Bambu Lab、Creality、Prusa、Elegoo、Klipper/Moonraker、OctoPrint、Duet/RepRapFirmware 以及任意 Marlin 打印机上完成设计、生成、切片与打印。Describe it or draw it — Kiln makes it real. The open-source MCP server for 3D printing: AI agents (Claude, Codex, Cursor, or any MCP client) design, generate, slice & print on Bambu Lab, Creality, Prusa, Elegoo, Klipper/Moonraker, OctoPrint, Duet/RepRapFirmware & any Marlin printer.

面向 AI agent 的本地优先、证据可控的学术写作工作流，具备受限修订、净室评审与发布治理能力。Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

智能多 agent 对话助手，采用 LangGraph 编排，支持 Human-in-the-Loop、企业级可观测性与完整 i18n 支持（6 种语言）。Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)

ImageTrans 插件集合。Plugins for ImageTrans

类 Notepad++ 风格的 LaTeX 编辑器，支持即时 PDF 预览和 SyncTeX，覆盖 Windows、Linux 和 macOS。Overleaf 的快速离线替代方案。Notepad++-style LaTeX editor with instant PDF preview and SyncTeX, for Windows, Linux and macOS. A fast, offline alternative to Overleaf

独立的 Skill 与 Codex 插件，支持 OpenAI 兼容的图像生成、编辑、批处理工作流、QA 以及聚焦画布编辑。Standalone Skill and Codex Plugin for OpenAI-compatible image generation, editing, batch workflows, QA, and focused canvas editing.

面向学术研究的 Claude Code 插件：基于 MCP 的引用、实证完整性保障、系统综述、Zotero 操作及并行批评式的稿件修订Claude Code plugin for academic research: MCP-grounded citations, empirical integrity, systematic reviews, Zotero operations, and parallel-critic manuscript revision.

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、HMI和Android双端；LLM 只负责理解与规划，VAL 负责确定性安全执行。

🎵 专属你的私人数字调音师|AI 音乐搜索推荐 Agent | 基于大模型 + 知识图谱 + 双模型声学向量的本地智能音乐推荐系统 | LLM-powered Music Recommendation Agent with Hybrid RAG, Neo4j, and Long-term Memory

面向 ECG-语言模型（ELM）的研究型训练与评估框架A research-oriented training and evaluation framework for ECG-Language Models (ELMs)

🚀 掌握 prompt engineering，通过指南、示例与最佳实践优化 AI 交互，覆盖各技能水平与应用领域。🚀 Master prompt engineering to optimize AI interactions with guides, examples, and best practices for all skill levels and domains.

运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

定位并修复 MCP 2026-07-28 规范修订给你的 server 带来的破坏。21 条规则、5 个自动修复器与一张就绪度看板。Find and fix what the MCP 2026-07-28 spec revision breaks in your server. 21 rules, 5 autofixers, and a readiness board.

用于学术写作的 Agentic Claude Code skills：评审模拟、修改与润色。Agentic Claude Code skills for academic writing: review simulation, revision, and prose improvement.

自托管 MCP 服务器，让你的 Obsidian/markdown 知识库可被任意 MCP 客户端检索——涵盖文本、PDF、Office 文档、图片与音频。基于类型化、可治理语料库的混合检索，5 万条笔记下仍可达亚秒级响应；文件保持纯 markdown。Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

MobileMem：面向持续演进 Agent 的设备端记忆MobileMem: On-Device Memory for Continually Evolving Agents

证据优先的具身 AI 研究枢纽，覆盖 VLA、世界模型、多模态感知、文献综述、声明审计以及可复用的 Agent skillEvidence-first Embodied AI research hub for VLA, world models, multimodal sensing, literature reviews, claim audits, and reusable agent skills.

每条声明均经机器校验，包括"零运行时守护进程"——受治理的 skill、规则与可回放状态。一份契约，适配所有宿主 AgentEvery claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

🤖 基于 AI 分析与智能搜索，定制化发现 ArXiv 上你感兴趣的最新论文🤖 Discover the latest research papers on ArXiv tailored to your interests using AI-powered analysis and smart search features.

基于 Keystone 构建的开发者友好型书籍发布模板，为精简变体——项目体积小，使用公共 Docker 镜像。Developer-friendly book publishing template built on Keystone. Slim variant — minimal project footprint, uses a public Docker image

可自托管且功能丰富的视频库Self-hostable and feature-rich video library

用于评估检索增强视觉语言模型在循证医学视觉问答中表现的研究框架Research framework evaluating retrieval-augmented vision-language models for evidence-grounded medical visual question answering.