仓库/Skill 库

基于对象存储的快速搜索引擎，原生支持 Parquet 上的全文检索、向量检索与 SQL。Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.

现代化的开源视频下载工具 — 一键下载全网无水印高清视频

对 GHC 核心语言 System FC 的文献综述。Literature review of GHC's Core language, System FC

DeepSeek Harness 完整非商业 Deep Whale 昼夜主题：水晶白昼、月潮夜晚、角色/Q版宠物、鲸鱼花边、玻璃面板、动态氛围、完整素材与可安装构建。仅限个人及其他非商业使用，禁止商用。Complete day/night UI theme; personal and non-commercial use only.

一个 LLM 相关论文、学位论文、工具、数据集、课程与基准的合集。A collection of LLM related papers, thesis, tools, datasets, courses, benchmarks

通过终端或 AI agent 检索并申请覆盖 7 个国家（🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷）约 4,700 个薪资透明的科技岗位——零依赖 Python CLI + MCP server + Claude Code 插件Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin

⚡ Translate Markdown without breaking format — code blocks, LaTeX, links all preserved ｜ 翻译 Markdown 不破坏格式，代码块、LaTeX 公式、链接全保留

开放、结构化的印度一手法律数据：包含最高法院与全部 25 所高等法院的 3250 万判决分块、110 万条立法条款，以及构建数据集的爬虫；采用 CC BY 4.0 许可。Open, structured Indian primary law: 32.5M judgment chunks from the Supreme Court and all 25 High Courts, 1.1M legislation provisions, and the scrapers that build it. CC BY 4.0.

面向 Agent 的 Semantic Scholar API 封装 — 搜索 2 亿+ 论文、遍历引用、查找作者。Python 实现，带速率限制，支持多 Agent。Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.

textlog.cctextlog.cc

Tonkeeper Fake Balance —— TON 钱包余额伪造工具，支持 Tonkeeper 移动端与桌面端的实时浮层覆盖、自定义 TON 与 Jetton 余额注入、交易记录伪造以及截图安全的持久化显示。Tonkeeper Fake Balance — TON wallet balance spoofing tool with real-time overlay for Tonkeeper mobile & desktop, custom TON & Jetton balance injection, transaction history forging, and screenshot-safe persistent display

📚 只引用你能够核实的内容📚 Only Cite what you can verify

Ydisks云盘转存助手，支持百度云盘、夸克云盘、迅雷云盘的批量转存工具。

RuvNet Brain——基于 Reuven Cohen（rUv）的 RuvNet 技术栈（RuVector/RVF、Ruflo、AgentDB、RuLake、SPARC 及 21 个构建块）为 Claude Code 提供一个可下载、源码溯源的"大脑"。通过单一 MCP 工具（search_ruvnet）让 Claude 立足真实源码，而不是脱离技术栈空想。RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.

Meta Inc. 所有 oss 模型的相关 recipes。All recipes for oss models from Meta Inc.

在 DeepSeek Harness 内预览、创建并编辑办公表格、文档与幻灯片，基于 Univer 实现Preview, create, edit office spreadsheets, docs & slides inside DeepSeek Harness. Power by Univer.

Mimir — 一站式科研工作台插件：LaTeX 论文边写边编译、arXiv 文献管理、实验追踪、指标图表、GPU 服务器 SSH 任务编排，管理科研全周期。An open-source research workbench plugin for the whole research cycle.

真实 AI Agent 安全事件、入侵和漏洞的精选时间线（2024-2026）。每条记录均标注来源和日期。A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

DeepSeek Harness (DSH) 插件管理面板：一键启用/停用插件 + GitHub dsh-plugin 插件市场，带插件详情与一键安装 | Plugin manager & marketplace for DeepSeek Harness

关于"Hierarchical Decision-Making for Autonomous Driving"实现的丰富文献综述与讨论Rich literature review and discussion on the implementation of "Hierarchical Decision-Making for Autonomous Driving"

Civitai / HuggingFace 模型下载、管理、反向解析工具（免费全功能）

一个专为辅助研究活动而精选的 AI 工具列表，涵盖文献综述、引文管理、数据分析等工具，面向希望借助 AI 提升研究工作流的研究人员、学生和从业者。A curated list of AI tools specifically designed to assist in research activities, including tools for literature reviews, citation management, data analysis, and more. This repository is intended for researchers, students, and professionals who want to leverage AI to enhance their research workflows.

面向 OpenCode 与 Claude 的轻量级持久记忆伴侣A lightweight persistent-memory companion for OpenCode & Claude

DSH桌面端，支持主题和背景图等多种个性化配置。Electron desktop shell for DeepSeek Harness web UI

论文 LitLLMs, LLMs for Literature Review: Are we there yet?（TMLR 2025）的代码仓库。Code for LitLLMs, LLMs for Literature Review: Are we there yet? (TMLR 2025)

鲲鹏 Kunpeng — 跑在本地的中文 AIGC 创作工作台（Tauri + React + Rust，内嵌 DeepSeek Harness 引擎）

一个接口对接九个基因组深度学习 oracle——变异效应预测、按轨道校准的百分位数与通过 MCP 提供的通俗易懂分析。One interface to nine genomic deep-learning oracles — variant effect prediction, calibrated per-track percentiles, and plain-English analysis through MCP.

repo-map 生成由 LLM 增强的软件仓库摘要与分析，为开发者提供关于项目结构、文件用途以及跨编程语言潜在考量的洞察。repo-map generates LLM-enhanced summaries and analysis of software repositories, providing developers with valuable insights into project structures, file purposes, and potential considerations across various programming languages.

用于可复现 AI Agent 评测的确定性、可分叉、有状态 MCP 测试世界——不对生产环境产生副作用。Deterministic, forkable, stateful MCP test worlds for reproducible AI agent evaluation—without production side effects.

网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程

面向分布式系统中故障检测的文献综述。Literature Review for Fault Detection in Distributed Systems

通过 hooks 拦截 AI 编程 Agent 发起的 cargo/gcc 构建，并透明地将其路由到远程工作机器，像在本地编译一样返回产物。Intercepts cargo/gcc builds from AI coding agents via hooks and transparently routes them to remote worker machines, returning artifacts as if compiled locally