仓库/Skill 库

GPU 加速的终端面板，将所有会话置于一张无限画布之上。GPU-accelerated terminal board that puts all your sessions on an infinite canvas

一站式AI学术论文写作辅助工具 · 支持从定题出稿全过程，涵盖降AIGC、查重率、润色、纠错等辅助功能

生成干净的 2D 游戏精灵图与动画图集——组件行流水线：状态行、alpha 清理、帧提取、运行时图集。Codex/Claude skill。Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

通过 MCP 为编码 Agent 提供开源跨 Agent 记忆层。兼容 Claude Code、Codex、Cursor、Windsurf、Gemini CLI、Antigravity、OpenClaw、Hermes Agent、Oh-my-Pi、Pi、Copilot、Kiro、OpenCode 与 Trae。Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

面向软件工程工作流的 Claude Code Skills——Git 自动化、测试和代码审查。Claude Code Skills for software engineering workflows - Git automation, testing, and code review

TypeScript 7 编译器（tsc）的实验性 Rust 移植An experimental Rust port of the TypeScript 7 compiler (tsc)

BioMCP：生物医学模型上下文协议。BioMCP: Biomedical Model Context Protocol

无需任何配置，即可在 Apple Silicon 上体验 Omarchy。Try Omarchy on Apple Silicon without any setup.

终端中的 AI 结对编程——单一静态二进制，亚毫秒级启动，支持任意模型。AI pair programming in your terminal — one static binary, sub-ms startup, any model

让幻灯片摆脱 AI 味的 Claude skill。品牌 DNA × 20 条编码化设计原则。A Claude skill for slides that don't look like AI made them. Brand DNA × 20 codified design principles.

33 种在终端中识别 AI 生成文本的方法。提供 before/after 示例、草稿检查器，零依赖。33 ways to spot AI-written text, right in your terminal. Before/after examples, draft checker, zero dependencies.

自动在目标社区发布个性化、真实评论的 Claude skill。A Claude skill that automatically posts personalized, authentic comments in your target communities.

把 AI 的 UI 设计能力推到极限。

长时程计算机使用 harness。让 AI Agent 在桌面应用与 CLI 中长时间运行，同时保持任务状态并在复杂工作流中可靠推进。具备全新上下文执行、持久化已验证状态、独立审计、可恢复进度以及原生 Claude Code / Codex / OpenClaw 集成。The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

你的个人 AIGC 工厂。任意图像，任意视频，以 Comfy 方式实现。©️Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

通用 LLM 网关：一个 API 对接所有 LLM。提供兼容 OpenAI/Anthropic 的端点，支持多 provider 转换与智能负载均衡。Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.

一个面向出版物元数据（pubmed、arxiv、medrxiv、biorxiv、chemrxiv）及引用分析的文献计量工具A bibliometrics tool for publication metadata (pubmed, arxiv, medrxiv, biorxiv, chemrxiv) and citation analyses

Claude skill，把你喜爱频道的 YouTube 转录文本转为 EPUB 电子书，定期投递到邮箱。Claude skill for turning YouTube transcripts from your favorite channels into EPUB ebooks, delivered to your email inbox regularly

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.

面向 LinkedIn 的 Claude skills。包含 11 项 Claude Code 和 Codex skills，可在终端中撰写自然的 LinkedIn 帖子、打造引人注意的评论、分析信息流并建立发布节奏。由 Creative Content Crafts 提供内容工程支持。MIT 许可。Claude skills for LinkedIn. 11 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.

DLSS 5 神经渲染，实时运行在你的整个 Windows 桌面上。支持 RTX 30/40/50，12 种语言，用户预设，带音频录制，单窗口模式。DLSS 5 Neural Rendering on your whole Windows desktop, in real time. RTX 30/40/50, 12 languages, user presets, recording with audio, one-window mode.

Krasis 是一个混合 LLM 运行时，专注于在消费级 VRAM 受限硬件上高效运行大模型Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

Parsifal 是一个辅助研究人员开展系统文献综述（SLR）的工具Parsifal is a tool to assist researchers to perform Systematic Literature Reviews

Adobe Illustrator 的开源 clean-room 纯 Rust 重新实现。An open-source, clean-room reimplementation of Adobe Illustrator, built in pure Rust.

自动化研究论文的发现与分析。例如，让计算机自动打开与任意 URL 论文最相似的文献，或找出在某数据集上报告结果的全部论文，重新定义文献综述Automating research publications discovery and analysis. For example, ever wish your computer could automatically open papers that are most similar to a paper at an arbitrary url? How about finding all papers that report results on some dataset? Let's re-imagine literature review.

降低学术论文 AIGC 查重率的 Claude Code Skill | A Claude Code skill for reducing AIGC detection rates in academic papers

从多源抓取学术研究论文Fetch Academic Research Papers from different sources

面向学术论文的 AI 驱动后处理工具包 —— 格式校验、语法/风格润色、去 AI 化编辑、参考文献核查，以及审稿人风格的论文审查。提供 LaTeX、Typst 和 PDF 的 5 个 Skill。专注于提升已有文本质量，而非从零生成AI-powered post-writing toolkit for academic papers — format validation, grammar/style polishing, de-AI editing, reference checking, and reviewer-style paper audits. 5 skills for LaTeX, Typst & PDF. Focused on enhancing existing text quality, not generating from scratch.

Claude skill，可基于 logo、文字或 emoji 生成 favicon、应用图标与社交媒体图片。支持 emoji 推荐、校验与框架自动集成。Claude skill to generate favicons, app icons, and social media images from logos, text, or emojis. Supports emoji suggestions, validation, and framework auto-integration.

本地运行开源决策模型：在兼容 TypeSafe 的 API 后面拉取并服务 Laya、decider、NLI 和 GLiClass。基于 Ollama 的决策模型。Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.

DeepSeek Harness (dsh) Windows 桌面客户端：内置 Node.js + dsh CLI，一键启动DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch

拓扑不动点理论：由两个公理推导标准模型、α⁻¹ 与宇宙学的机器可验证离散编译器。包含论文、验证套件（Python/Wolfram/Lean）、实验及网站。Topological Fixed-Point Theory: a machine-checked discrete compiler for the Standard Model, α⁻¹, and cosmology from two axioms. Papers, verification suite (Python/Wolfram/Lean), experiments & website.

面向 AI Agent 的上下文工程。token 消耗减少约 80%。解决工具过载问题。内置进程内 BM25 与语义检索的 Skill 与 memory。支持渐进式披露（Progressive Disclosure）。无需向量数据库。Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

观察 agent 的思考过程。为 30 种 AI agent runtime 提供零配置可观测性与治理：Claude Code、OpenAI Codex、Hermes、OpenClaw 等 26+。实时 token 成本、会话、tool calls、crons。See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.