[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"home-tools-en":3,"home-skills-en":108},{"items":4,"total":105,"page":106,"pageSize":107},[5,30,45,60,75,90],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":10,"categoryName":11,"sourceUrl":12,"homepageUrl":-1,"downloadUrl":13,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":14,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":17,"clients":20,"tags":27,"installCommand":-1,"configSnippet":-1,"useCases":28,"updatedAt":29},"yzfly-awesome-mcp-zh","yzfly\u002Fawesome-mcp-zh","devtools","MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients","欢迎来到 Awesome-MCP-ZH，一个专为中文用户打造的 MCP（模型上下文协议）资源合集！ 这里有 MCP 的基础介绍、玩法、客户端、服务器和社区资源，帮你快速上手这个 AI 界的“万能插头”。\n\n- 如果国内的朋友想免费快速的体验MCP能力，推荐 Cherry Studio（客户端） + 阿里 Qwen (大模型）的组合，优势是免费、操作简单、LLM无需魔法、无需充值。\n\n- LLM 选型我的使用体感是： Claude4.5 > GPT-5 > Gemini-2.5 > Qwen3-Max > DeepSeek\n\n分析文章： - 10分钟搞定高德地图MCP！我用AI解决了约会地点选择难题 - 因为Manus爆火的 Claude MCP，90%人的认知可能都是错的 - 刚官宣支持MCP，就发布自家Agent协议（A2A），扒一扒Google暗藏的小心思 - 阿里云拥抱 MCP 这步棋，太多人都没有真正看懂 - 详解 MCP 传输机制\n\nMCP 全称 ，由 Anthropic 在 2024 年 11 月推出，是个开源通信标准。简单说，它给 AI 装了个“超级网线”，让 AI 能跟外部工具、数据、系统无缝对接。\n\n- ：AI 是个聪明但宅家的书呆子，MCP 就是它的“外卖员”，能帮它拿数据、干活儿。 - ：让 AI 不只聊天，还能真动手，比如查数据库、发邮件、写代码。\n\n微软出的面向初学者的 Model Context Protocol (MCP) 课程也不错，推荐一下： - mcp-for-beginners\n\n1. ：用 Slack 发消息、用 GitHub 管代码、用 Blender 建 3D 模型。 2. ：直接看你电脑文件、数据库记录，甚至网上实时信息。 3. ：写网页时，AI 能查代码、生成图片、调试页面，一条龙搞定。 4. ：AI 干一半问你意见，你点头它再继续。","Developer tools","https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-mcp-zh","https:\u002F\u002Fgithub.com\u002Fyzfly\u002Fawesome-mcp-zh\u002Farchive\u002FHEAD.zip",7381,0,99,[18,19],"claude-desktop","cursor",[21,24],{"slug":18,"name":22,"summary":23,"count":15},"Claude Desktop","Desktop client with local MCP configuration support.",{"slug":19,"name":25,"summary":26,"count":15},"Cursor","AI code editor frequently used with developer-focused MCP servers.",[8],[],"2026-08-30T04:31:20.847612",{"slug":31,"name":32,"categorySlug":8,"summary":33,"description":34,"categoryName":11,"sourceUrl":35,"homepageUrl":-1,"downloadUrl":36,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":37,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":38,"clients":39,"tags":42,"installCommand":-1,"configSnippet":-1,"useCases":43,"updatedAt":44},"sansan0-trendradar","sansan0\u002Ftrendradar","⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。","- 感谢** 的观众们， 你所欲也， 我所欲也，两者得兼😍是对开源精神最好的支持\n\n💡 ： 1. ：下方表格记录了项目起步阶段（天使轮）的支持者。因早期人工统计繁琐，。 2. ：为了将有限的精力回归代码与功能迭代，。 无论名字是否上榜，你们的每一份支持都是 TrendRadar 能够走到今天的基石。🙏\n\n本项目使用 newsnow 项目的 API 获取多平台数据，特别感谢作者提供的服务。\n\n经联系，作者表示无需担心服务器压力，但这是基于他的善意和信任。请大家： - - Docker 部署时，请合理控制推送频率，勿竭泽而渔\n\n感谢**的朋友们，你们的慷慨已化身为键盘旁的零食饮料，陪伴着项目的每一次迭代。 ： 随着 v5.0.0 版本的发布，项目迈入了一个新的阶段。为了支持日益增长的 API 成本和咖啡因消耗，\"一元点赞\"通道现已重新开启。你的每一份心意，都将转化为代码世界里的 Token 和动力。🚀 前往支持\n\n若 TrendRadar 曾为你捕捉价值，不妨为它注入动力，助其持续进化 金额随意，1 元也是对开源的鼓励。欢迎在赞赏时备注留言 (´▽`ʃ♡ƪ)\n\n如果你在项目中使用或借鉴了本项目的思路、核心代码，**在 README 或文档中注明来源并附上本仓库链接。\n\n- ：适合具体的技术问题。提问时请提供完整信息（截图、错误日志等），有助于快速定位。 - ：建议优先在相关文章下的留言区交流。若需后台提问，**文章是最好的\"敲门砖\"，我在后台都能感受到这份心意哟 (´▽`ʃ♡ƪ)。 - ：关注公众号，回复「」即可加入。无论你是 AI 小白还是硬核开发者，想求助技术问题还是分享折腾心得，这里都欢迎你。群里主打互助交流和灵感碰撞，入群请先看群公告；提问时描述清楚问题、附上截图，群友有空就会帮忙，大家的实战经验往往比我一个人更快更全面 🤝","https:\u002F\u002Fgithub.com\u002Fsansan0\u002Ftrendradar","https:\u002F\u002Fgithub.com\u002Fsansan0\u002Ftrendradar\u002Farchive\u002FHEAD.zip",60418,[18,19],[40,41],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:10.12732",{"slug":46,"name":47,"categorySlug":8,"summary":48,"description":49,"categoryName":11,"sourceUrl":50,"homepageUrl":-1,"downloadUrl":51,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":52,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":53,"clients":54,"tags":57,"installCommand":-1,"configSnippet":-1,"useCases":58,"updatedAt":59},"microsoft-playwright-mcp","microsoft\u002Fplaywright-mcp","Playwright MCP server","A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.\n\nThis package provides MCP interface into Playwright. If you are using a , you might benefit from using the CLI+SKILLS instead.\n\n- : Modern increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows. .","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp\u002Farchive\u002FHEAD.zip",34581,[18,19],[55,56],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:02.803732",{"slug":61,"name":62,"categorySlug":8,"summary":63,"description":64,"categoryName":11,"sourceUrl":65,"homepageUrl":-1,"downloadUrl":66,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":67,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":68,"clients":69,"tags":72,"installCommand":-1,"configSnippet":-1,"useCases":73,"updatedAt":74},"liaokongvfx-mcp-chinese-getting-started-guide","liaokongvfx\u002Fmcp-chinese-getting-started-guide","Model Context Protocol(MCP) 编程极速入门","模型上下文协议（MCP）是一个创新的开源协议，它重新定义了大语言模型（LLM）与外部世界的互动方式。MCP 提供了一种标准化方法，使任意大语言模型能够轻松连接各种数据源和工具，实现信息的无缝访问和处理。MCP 就像是 AI 应用程序的 USB-C 接口，为 AI 模型提供了一种标准化的方式来连接不同的数据源和工具。\n\n- Resources 资源 - Prompts 提示词 - Tools 工具 - Sampling 采样 - Roots 根目录 - Transports 传输层\n\n因为大部分功能其实都是服务于 Claude 客户端的，本文更希望编写的 MCP 服务器服务与通用大语言模型，所以本文将会主要以“工具”为重点，其他功能会放到最后进行简单讲解。\n\n其中 MCP 的传输层支持了 2 种协议的实现：stdio（标准输入\u002F输出）和 SSE（服务器发送事件），因为 stdio 更为常用，所以本文会以 stdio 为例进行讲解。\n\n本文将会使用 3.11 的 Python 版本，并使用 uv 来管理 Python 项目。同时代码将会在文末放到 Github 上，废话不多说，我们这就开始吧~\n\n在这一小节中，我们将会实现一个用于网络搜索的服务器。首先，我们先来通过 uv 初始化我们的项目。\n\n然后我们来创建一个叫 web_search.py 文件，来实现我们的服务。MCP 为我们提供了2个对象：mcp.server.FastMCP 和 mcp.server.Server，mcp.server.FastMCP 是更高层的封装，我们这里就来使用它。\n\n实现执行的方法非常简单，MCP 为我们提供了一个 @mcp.tool() 我们只需要将实现函数用这个装饰器装饰即可。函数名称将作为工具名称，参数将作为工具参数，并通过注释来描述工具与参数，以及返回值。","https:\u002F\u002Fgithub.com\u002Fliaokongvfx\u002Fmcp-chinese-getting-started-guide","https:\u002F\u002Fgithub.com\u002Fliaokongvfx\u002Fmcp-chinese-getting-started-guide\u002Farchive\u002FHEAD.zip",3536,[18,19],[70,71],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:30:38.131225",{"slug":76,"name":77,"categorySlug":8,"summary":78,"description":79,"categoryName":11,"sourceUrl":80,"homepageUrl":-1,"downloadUrl":81,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":82,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":83,"clients":84,"tags":87,"installCommand":-1,"configSnippet":-1,"useCases":88,"updatedAt":89},"supabase-mcp","supabase\u002Fmcp","Connect Supabase to your AI assistants","Connect your Supabase projects to Cursor, Claude, Windsurf, and other AI assistants.\n\nThe Model Context Protocol (MCP) standardizes how Large Language Models (LLMs) talk to external services like Supabase. It connects AI assistants directly with your Supabase project and allows them to perform tasks like managing tables, fetching config, and querying data. See the full list of tools.\n\nBefore setting up the MCP server, we recommend you read our security best practices to understand the risks of connecting an LLM to your Supabase projects and how to mitigate them.\n\nTo configure the Supabase MCP server on your client, visit our setup documentation. You can also generate a custom MCP URL for your project by visiting the MCP connection tab in the Supabase dashboard.\n\nYour MCP client will automatically prompt you to log in to Supabase during setup. Be sure to choose the organization that contains the project you wish to work with.","https:\u002F\u002Fgithub.com\u002Fsupabase\u002Fmcp","https:\u002F\u002Fgithub.com\u002Fsupabase\u002Fmcp\u002Farchive\u002FHEAD.zip",2777,[18,19],[85,86],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:30:41.054294",{"slug":91,"name":92,"categorySlug":8,"summary":93,"description":94,"categoryName":11,"sourceUrl":95,"homepageUrl":-1,"downloadUrl":96,"cliCommand":-1,"primaryLanguage":-1,"license":-1,"stars":97,"forks":15,"trendScore":16,"qualityScore":16,"supportedClients":98,"clients":99,"tags":102,"installCommand":-1,"configSnippet":-1,"useCases":103,"updatedAt":104},"kyopark2014-mcp","kyopark2014\u002Fmcp","It shows how to use model-context-protocol.","MCP(Model Context Protocol)은 생성형 AI application이 외부 데이터를 활용하는 주요한 인터페이스로 빠르게 확산되고 있습니다. 2024년 11월에 Anthropic의 오픈소스 프로젝트로 시작되었고, 현재 Cursor뿐 아니라 OpenAI에서도 지원하고 있습니다. 여기에서는 MCP with LangChain을 이용하여 LangGraph로 만든 application이 MCP를 활용하는 방법에 대해 설명합니다. 여기서 구현한 RAG는 Amazon의 완전관리형 RAG 서비스인 Knowledge base로 구현되었으므로, 문서의 텍스트 추출, 동기화, chunking과 같은 작업을 손쉽게 수행할 수 있으며, 멀티모달을 이용해 이미지\u002F표를 분석할 수 있습니다. 여기에서는 MCP server에서 RAG에 손쉽게 접근할 수 있도록 AWS Lambda를 이용해 API를 구성하였습니다.\n\n아래 architecture는 AWS 환경에서 MCP를 포함한 Agent를 구성하는것을 보여줍니다. Agent는 MCP server\u002Fclient 구조를 활용하여 외부의 데이터 소스를 활용할 수 있습니다. MCP client는 MCP server와 JSON-RPC 프로토콜에 기반하여 stdio\u002FSSE로 통신을 수행합니다. Stdio 사용시 MCP Server는 python, java와 같은 코드로 구성이 되고, client에서 요청이 오면 RAG나 인터넷등을 이용해 데이터를 수집하거나 전달하는 역할을 수행합니다. SSE로 할 경우에 MCP client와 server는 IP로 통신을 하게 됩니다. 여기서는 Streamlit을 이용해 application의 UI를 구성하고, 사용자는 ALB - CloudFront를 이용해 HTTPS 방식으로 브라우저를 통해 application을 이용합니다. 또한, 여기에서는 커스터마이징이 유리한 LangGraph를 이용해 MCP 기반의 application을 개발하는것을 설명합니다.","https:\u002F\u002Fgithub.com\u002Fkyopark2014\u002Fmcp","https:\u002F\u002Fgithub.com\u002Fkyopark2014\u002Fmcp\u002Farchive\u002FHEAD.zip",40,[18,19],[100,101],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:31:29.078586",5055,1,6,{"items":109,"total":210,"page":106,"pageSize":107},[110,127,144,160,176,193],{"slug":111,"name":112,"title":112,"skillCategorySlug":8,"summary":113,"description":114,"skillCategoryName":11,"sourceUrl":115,"downloadUrl":116,"cliCommand":117,"authorName":-1,"version":-1,"license":-1,"stars":118,"trendScore":16,"qualityScore":16,"recommendedTools":119,"recommendedToolNames":119,"supportedClients":120,"clients":121,"tags":124,"installHint":117,"useCases":125,"updatedAt":126},"rohitg00-ai-engineering-from-scratch","rohitg00\u002Fai-engineering-from-scratch","Learn it. Build it. Ship it for others.","This curriculum closes that gap. 503 lessons. 20 phases. ~320 hours. Python, TypeScript, Rust, Julia. Every lesson ships a reusable artifact: a prompt, a skill, an agent, an MCP server. Free, open source, MIT. You don't just learn AI. You build it. End-to-end. By hand.\n\n150,639 readers  ·  241,669 page views in the last 30 days  ·  as of 2026-06-07\n\nMost AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it.\n\nThis curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop.","https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fai-engineering-from-scratch","https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fai-engineering-from-scratch\u002Farchive\u002FHEAD.zip","npx skillfish add rohitg00\u002Fai-engineering-from-scratch",37409,[],[18,19],[122,123],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:42:34.08289",{"slug":128,"name":129,"title":129,"skillCategorySlug":8,"summary":130,"description":131,"skillCategoryName":11,"sourceUrl":132,"downloadUrl":133,"cliCommand":134,"authorName":-1,"version":-1,"license":-1,"stars":135,"trendScore":16,"qualityScore":16,"recommendedTools":136,"recommendedToolNames":136,"supportedClients":137,"clients":138,"tags":141,"installHint":134,"useCases":142,"updatedAt":143},"avdlee-swiftui-agent-skill","avdlee\u002Fswiftui-agent-skill","Add expert SwiftUI Best Practices guidance to your AI coding tool (Agent Skills open format).","Expert guidance for any AI coding tool that supports the Agent Skills open format — SwiftUI state management, view composition, performance, and iOS 26+ Liquid Glass adoption.\n\nThis repository distills practical SwiftUI best practices into actionable, concise references for agents and code review workflows.\n\n- Teams adopting modern SwiftUI APIs who want quick, correct defaults - Developers reviewing or refactoring SwiftUI views and data flow - Anyone shipping performant lists, scrolling, sheets, and navigation in SwiftUI\n\n- Swift Concurrency Expert - Core Data Expert - Swift Testing Expert - Xcode Build Optimization Agent Skill - Xcode Simulator AI Control Agent Skill\n\nInstall this skill with a single command:\n\nFor more information, visit the skills.sh platform page.","https:\u002F\u002Fgithub.com\u002Favdlee\u002Fswiftui-agent-skill","https:\u002F\u002Fgithub.com\u002Favdlee\u002Fswiftui-agent-skill\u002Farchive\u002FHEAD.zip","npx skillfish add avdlee\u002Fswiftui-agent-skill",3189,[],[18,19],[139,140],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:27:59.920097",{"slug":145,"name":146,"title":146,"skillCategorySlug":8,"summary":147,"description":147,"skillCategoryName":11,"sourceUrl":148,"downloadUrl":149,"cliCommand":150,"authorName":-1,"version":-1,"license":-1,"stars":151,"trendScore":16,"qualityScore":16,"recommendedTools":152,"recommendedToolNames":152,"supportedClients":153,"clients":154,"tags":157,"installHint":150,"useCases":158,"updatedAt":159},"composiohq-awesome-codex-skills","composiohq\u002Fawesome-codex-skills","A curated list of practical Codex skills for automating workflows across the Codex CLI and API.","https:\u002F\u002Fgithub.com\u002Fcomposiohq\u002Fawesome-codex-skills","https:\u002F\u002Fgithub.com\u002Fcomposiohq\u002Fawesome-codex-skills\u002Farchive\u002FHEAD.zip","npx skillfish add composiohq\u002Fawesome-codex-skills",14453,[],[18,19],[155,156],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T01:41:09.707942",{"slug":161,"name":162,"title":162,"skillCategorySlug":8,"summary":163,"description":163,"skillCategoryName":11,"sourceUrl":164,"downloadUrl":165,"cliCommand":166,"authorName":-1,"version":-1,"license":-1,"stars":167,"trendScore":16,"qualityScore":16,"recommendedTools":168,"recommendedToolNames":168,"supportedClients":169,"clients":170,"tags":173,"installHint":166,"useCases":174,"updatedAt":175},"kkkkhazix-khazix-skills","kkkkhazix\u002Fkhazix-skills","I am khazix, a digital life form, founder of Xushi Media, striving to share some interesting AI insights, and may we always remain curious about the world.","https:\u002F\u002Fgithub.com\u002Fkkkkhazix\u002Fkhazix-skills","https:\u002F\u002Fgithub.com\u002Fkkkkhazix\u002Fkhazix-skills\u002Farchive\u002FHEAD.zip","npx skillfish add kkkkhazix\u002Fkhazix-skills",16318,[],[18,19],[171,172],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T01:38:27.368515",{"slug":177,"name":178,"title":178,"skillCategorySlug":8,"summary":179,"description":180,"skillCategoryName":11,"sourceUrl":181,"downloadUrl":182,"cliCommand":183,"authorName":-1,"version":-1,"license":-1,"stars":184,"trendScore":16,"qualityScore":16,"recommendedTools":185,"recommendedToolNames":185,"supportedClients":186,"clients":187,"tags":190,"installHint":183,"useCases":191,"updatedAt":192},"diegosouzapw-awesome-omni-skill","diegosouzapw\u002Fawesome-omni-skill","Repositorio Publico, agregador de skills","The largest curated collection of SKILL.md-compatible agent skills for Claude Code, Gemini CLI, Cursor, Copilot, and more. Auto-synced from OmniSkill Registry.\n\nVisit the OmniSkill Registry for search, filters, and one-click install commands.\n\nSee CATALOG.md for the complete alphabetical listing of all 10,000 skills.\n\nThis repo is automatically synced from OmniSkill Registry every 6 hours via GitHub Actions.\n\nEach skill directory contains: - SKILL.md — The original skill file from the source repository - metadata.json — Rich metadata including quality score, stars, install commands, and source links\n\nThis repository is an . All skills are sourced from their original repositories. Links to source repos are preserved in each metadata.json. All credit goes to the original authors.\n\nIndividual skills retain their original licenses. This aggregation layer is MIT licensed.","https:\u002F\u002Fgithub.com\u002Fdiegosouzapw\u002Fawesome-omni-skill","https:\u002F\u002Fgithub.com\u002Fdiegosouzapw\u002Fawesome-omni-skill\u002Farchive\u002FHEAD.zip","npx skillfish add diegosouzapw\u002Fawesome-omni-skill",53,[],[18,19],[188,189],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T04:41:46.245546",{"slug":194,"name":195,"title":195,"skillCategorySlug":8,"summary":196,"description":197,"skillCategoryName":11,"sourceUrl":198,"downloadUrl":199,"cliCommand":200,"authorName":-1,"version":-1,"license":-1,"stars":201,"trendScore":16,"qualityScore":16,"recommendedTools":202,"recommendedToolNames":202,"supportedClients":203,"clients":204,"tags":207,"installHint":200,"useCases":208,"updatedAt":209},"run-llama-liteparse","run-llama\u002Fliteparse","A fast, helpful, and open-source document parser","Looking for LiteParse V1? Follow this link to the old code\n\nLiteParse is a standalone OSS PDF parsing tool focused exclusively on parsing. It provides high-quality spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. Everything runs locally on your machine.\n\nFor complex documents (dense tables, multi-column layouts, charts, handwritten text, or scanned PDFs), you'll get significantly better results with LlamaParse, our cloud-based document parser built for production document pipelines. LlamaParse handles the hard stuff so your models see clean, structured data and markdown.","https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fliteparse","https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fliteparse\u002Farchive\u002FHEAD.zip","npx skillfish add run-llama\u002Fliteparse",11474,[],[18,19],[205,206],{"slug":18,"name":22,"summary":23,"count":15},{"slug":19,"name":25,"summary":26,"count":15},[8],[],"2026-08-30T08:28:40.625271",4585]