仓库/Skill 库

DeepSpec：用于训练与评估推测解码（speculative decoding）算法的全栈代码库DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

使用 LaTeX 编写的软件开发者简历Software developer resume in Latex

面向并利用基础模型的数据处理！🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Git. Ship. Done - CoreGit. Ship. Done - Core

ClearML —— 以自动化 CI/CD 简化 AI 工作负载。一站式 MLOps/LLMOps 解决方案，涵盖实验管理、数据管理、pipeline、编排、调度与服务。ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

A股全栈数据工具包 · 10层架构 · 40端点 · 13数据源 · 行情/研报(个股+行业)/资金面/筹码/公告/打板/ETF期权/舆情互动全覆盖 | China A-Share full-stack data toolkit (40 endpoints)

开源全球情报平台——实时 OSINT 仪表盘——Palantir 替代方案——按交易量抽取 0.5%，钱包地址 2nZNHm3Lr9umG3DVrzYwHgktwkuKuJRXqqRqs3ewpumpOpen Source Global Intelligence Platform - Real-Time OSINT Dashboard - A Palantir Alternative - We Get 0.5% on Volume Traded 2nZNHm3Lr9umG3DVrzYwHgktwkuKuJRXqqRqs3ewpump

🥣 AIGC 提示词可视化编辑器 | OPS | Open Prompt Studio

提供威胁建模、扫描、分诊、修补等技能，以及一个可通过 /customize 定制的自主扫描 harness。Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

数分钟内（而非数月）将 AI Agents 部署到 Google Cloud。提供生产就绪模板，内置 CI/CD、评估和可观测性。Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

让 Agent 具备浏览器使用能力的 Claude Skill。A Claude Skill to give your agent the ability to use a web browser

通过将文本上下文渲染为图像，将 Fable 5 的 token 使用量降低cut Fable 5 token usage by rendering text context as images

用于构建 agentic apps 的开源框架，支持 JavaScript、Go、Dart 与 Python，由 Google 在生产环境中构建并使用。Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

VimTeX：面向 LaTeX 文件的现代 Vim 与 neovim 文件类型插件VimTeX: A modern Vim and neovim filetype plugin for LaTeX files.

面向 Apple Silicon 的端侧语音 AI。On-device Speech AI for Apple Silicon

中文 CSL 样式 - Zotero 中文社区

三语（繁中 / English / 简中）Agentic AI 学习路线图：从 LLM 基础到多 Agent 系统，收录 240+ 精选资源与动手示例。中文 AI agent 學習地圖。A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

Mooncake 是 Moonshot AI 旗下领先 LLM 服务 Kimi 的服务平台。Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

一款提供 iOS 与 macOS 项目开发工具的 Model Context Protocol (MCP) server 与 CLI，供 Agent 使用。A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

找到在你的硬件上真正能跑且性能最优的本地 LLM。排名基于真实且时新的基准测试，而非参数量。一条命令，即刻运行。Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

美股指南

原子化构建 AI AgentBuilding AI agents, atomically

教程、指南与 Agent Skill 目录。Tutorials, Guides and Agent Skills Directories

🧊 开源 LLM 可观测性平台，一行代码即可实现监控、评估与实验。YC W23 🍓🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

面向全模态模型的高效推理框架。A framework for efficient model inference with omni-modality models

面向 ML/CV/NLP 论文写作的 Skill 包，基于彭思达教授关于 Codex、Claude Code 和 Gemini 的开放笔记整理与改编而成。Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.

将Typora伪装成LaTeX的中文样式主题，本科生轻量级课程论文撰写的好帮手。This is a theme disguising Typora into Chinese LaTeX style.

Google Cloud Knowledge Catalog 工具与示例Google Cloud Knowledge Catalog Tools and Samples

为开发者精选的 LLMOps 工具 awesome 列表An awesome & curated list of best LLMOps tools for developers

AI Agent 治理工具包 —— 提供策略执行、零信任身份、运行沙箱与可靠性工程，覆盖 OWASP Agentic Top 10 全部 10 项。AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

为 Agent 打造的快速精准代码搜索，相比 grep+read 减少约 98% 的 token 用量。Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

通过 CLI、Model Context Protocol (MCP) server 和 AI Agent Skill 编程访问 Gemini Notebook。Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context Protocol (MCP) server, and AI agent skills.

根据你的 Zotero 库，每日推荐你感兴趣的新 arxiv 论文。Recommend new arxiv papers of your interest daily according to your Zotero libarary.

AI 原生网络安全的执行系统——意图转化为受治理的执行，证据成为可运营的记忆，每一次操作都让下一次更优。The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

Anthony Fu 精选的 Agent Skill 集合。Anthony Fu's curated collection of agent skills.

🐢 面向 LLM Agent 的开源评估与测试库🐢 Open-Source Evaluation & Testing library for LLM Agents