[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-feishu-open-source-cli-ai-agent-office-en":3,"article-related-feishu-open-source-cli-ai-agent-office-en":25,"series-tools-1071fe0e-fa5f-4e00-b504-db3b6e5c266b":75},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":11,"views":22,"created_at":23,"published_at":24,"topic_cluster_id":11},"1071fe0e-fa5f-4e00-b504-db3b6e5c266b","feishu-open-source-cli-ai-agent-office-en","飞书开源CLI：AI Agent 直接管办公协作","\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.feishu.cn\u002F\" target=\"_blank\" rel=\"noopener\">飞书\u003C\u002Fa>这次开源的不是一个小脚本，而是一套能把办公软件变成 AI Agent 操作对象的 CLI。项目提供 200+ 命令和 19 个 AI Agent Skills，覆盖日历、文档、多维表格、消息等核心协作场景。\u003C\u002Fp>\u003Cp>如果你平时已经在用 \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fclaude-code\" target=\"_blank\" rel=\"noopener\">Claude Code\u003C\u002Fa>、\u003Ca href=\"https:\u002F\u002Fwww.cursor.com\u002F\" target=\"_blank\" rel=\"noopener\">Cursor\u003C\u002Fa> 这类编程助手，这个项目的意义很直接：AI 不再只是帮你写代码，它还能帮你改日程、查文档、发消息、整理表格。办公软件第一次像开发工具一样，能被命令行直接驱动。\u003C\u002Fp>\u003Cp>这类工具之所以值得关注，不是因为“AI 能做更多事”这种空话，而是因为它把企业协作系统接进了 AI 工作流。对于开发者来说，这意味着一个新的接口层；对于团队来说，这意味着很多原本靠人工点来点去的流程，终于可以被脚本化、自动化。\u003C\u002Fp>\u003Ch2>飞书 CLI 到底做了什么\u003C\u002Fh2>\u003Cp>从公开信息看，这个 \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffeishu-open\u002Ffeishu-cli\" target=\"_blank\" rel=\"noopener\">飞书 CLI\u003C\u002Fa> 项目把飞书的能力拆成了可调用的命令集合，再包装成适合 AI Agent 理解的 Skills。换句话说，AI 不需要“看懂”整个飞书界面，只要学会调用这些命令，就能完成大部分协作动作。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057899643-ocat.png\" alt=\"飞书开源CLI：AI Agent 直接管办公协作\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>它覆盖的范围很广：日历安排、文档编辑、多维表格操作、消息收发，基本都是办公室里最常见的高频动作。对很多团队来说，这些动作每天重复几十次，真正消耗时间的不是决策，而是执行。\u003C\u002Fp>\u003Cp>如果把这件事放到产品层面看，飞书做的是一层标准化操作接口；放到 AI 层面看，它做的是一层工具适配。两层叠在一起，AI Agent 才能从“会聊天的助手”变成“能干活的执行者”。\u003C\u002Fp>\u003Cul>\u003Cli>200+ 命令，覆盖飞书核心协作功能\u003C\u002Fli>\u003Cli>19 个 AI Agent Skills，方便 Claude Code、Cursor 这类工具直接调用\u003C\u002Fli>\u003Cli>支持日历、文档、多维表格、消息等高频场景\u003C\u002Fli>\u003Cli>项目开源，开发者可以直接查看实现方式并二次集成\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>为什么这类 CLI 很重要\u003C\u002Fh2>\u003Cp>很多人对 AI 办公自动化的想象还停留在“写邮件草稿”或“总结会议纪要”。但真正能省时间的，往往是那些看起来不起眼的中间步骤：建会、改时间、补资料、同步群消息、更新表格、拉取文档链接。\u003C\u002Fp>\u003Cp>飞书 CLI 的价值就在这里。它把这些步骤变成了结构化命令，AI 只要理解意图，就能把任务拆成一串可执行动作。对开发者而言，这种设计比单纯做一个聊天机器人更实用，因为它直接接到了工作流末端。\u003C\u002Fp>\u003Cp>我更看重的是它对“办公软件 API 化”的推动。过去企业软件常常把功能藏在 UI 后面，自动化只能靠网页抓取、RPA 或者零散接口。现在，AI Agent 需要的是更稳定、更明确的工具层，CLI 正好补上这一环。\u003C\u002Fp>\u003Cblockquote>“The future of work is not about working harder, but about working smarter.” — Satya Nadella\u003C\u002Fblockquote>\u003Cp>这句话经常被引用，但放在这里并不空。飞书 CLI 的思路就是把“更聪明地工作”落到可执行命令上，而不是停留在概念演示里。Satya Nadella 说这句话时谈的是工作方式变化，而这类工具正是在把变化变成日常操作。\u003C\u002Fp>\u003Ch2>和传统办公自动化比，差别在哪\u003C\u002Fh2>\u003Cp>传统办公自动化通常靠宏、RPA、Webhook 或者内部脚本。它们能做事，但问题也很明显：配置成本高、维护麻烦、对界面变化敏感，而且很难让 AI 直接参与决策和执行。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057932912-qpwq.png\" alt=\"飞书开源CLI：AI Agent 直接管办公协作\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>飞书 CLI 的做法更适合 AI 原生工作流。它把能力暴露为命令，再让模型通过 Skills 去理解这些命令的用途。这样一来，AI 不需要“猜”按钮在哪里，只要按命令执行就行。\u003C\u002Fp>\u003Cp>如果和常见工具做个对比，差异会更直观：\u003C\u002Fp>\u003Cul>\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fmicrosoft-365\" target=\"_blank\" rel=\"noopener\">Microsoft 365\u003C\u002Fa> 的自动化更依赖 Power Automate 和生态集成，适合流程编排，但对 AI Agent 直控的支持没有 CLI 这么直接\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fworkspace.google.com\u002F\" target=\"_blank\" rel=\"noopener\">Google Workspace\u003C\u002Fa> 依赖 Apps Script 和 API，开发者体验不错，但更偏传统开发模型\u003C\u002Fli>\u003Cli>飞书 CLI 把可执行动作压缩到命令行，适合 Claude Code、Cursor 这类工具在同一工作流里直接调用\u003C\u002Fli>\u003Cli>200+ 命令意味着它不是只做几个演示级功能，而是覆盖了较完整的协作操作面\u003C\u002Fli>\u003C\u002Ful>\u003Cp>从效率角度看，这种差别很现实。一个 AI Agent 如果能直接调用命令完成任务，就不需要人工在多个页面之间切换，也不需要为每个动作单独设计复杂插件。对于团队内部工具链来说，这会明显降低集成门槛。\u003C\u002Fp>\u003Ch2>开发者为什么会关心它\u003C\u002Fh2>\u003Cp>这类项目最吸引开发者的地方，不是“飞书能不能被 AI 控制”，而是“企业软件能不能像开发工具一样被编排”。如果答案是可以，那很多内部系统都会迎来新的交互方式。\u003C\u002Fp>\u003Cp>飞书 CLI 也给了一个很具体的信号：企业协作软件正在进入工具可组合阶段。AI Agent 不再只调用通用大模型接口，而是开始调用有明确语义的业务命令。这比“让模型读一堆文档再自己猜”要可靠得多。\u003C\u002Fp>\u003Cp>我认为这会影响两类团队。第一类是已经在做 AI 办公助手、内部知识库、流程自动化的团队。第二类是平台工程或开发者体验团队，他们会开始思考：我们的系统能不能也提供一层 CLI，让 AI 直接接上来？\u003C\u002Fp>\u003Cp>如果你想把这种思路放进自己的项目，可以先看两个方向：一是把高频操作抽成稳定命令；二是给命令补上清晰的参数和返回值。AI 最怕模糊接口，最喜欢结构化输入输出。\u003C\u002Fp>\u003Ch2>接下来会发生什么\u003C\u002Fh2>\u003Cp>飞书开源 CLI 这件事，真正值得下注的不是“能不能让 AI 发消息”，而是它会不会成为企业软件的新默认接口之一。只要更多厂商开始把核心功能做成可调用命令，AI Agent 就会从“会用工具”变成“直接操作系统”。\u003C\u002Fp>\u003Cp>短期内，最先受益的会是那些已经把 \u003Ca href=\"\u002Fnews\u002Fclaude-code-march-2026-update-fixes-bugs-en\">Claude Code\u003C\u002Fa>、Cursor、Copilot 一类工具融入日常工作的团队。它们会最早发现：当日历、文档和消息都能被命令行驱动时，很多协作流程会变得更短、更自动化，也更适合批量处理。\u003C\u002Fp>\u003Cp>更具体一点，我的判断是，接下来 12 个月里，企业软件会出现更多类似的开源 CLI 和 Agent Skills 包装层。谁先把“可执行接口”做得更完整，谁就更容易进入 AI 工作流。问题已经不是 AI 能不能碰办公软件，而是你的系统有没有准备好让 AI 直接动手。\u003C\u002Fp>\u003Cp>如果你是开发者，现在就该问自己一个问题：你的内部工具，能不能像飞书 CLI 这样，被 AI 一条命令接管？\u003C\u002Fp>","飞书开源 CLI 提供 200+ 命令和 19 个 AI Skills，让 Claude Code、Cursor 直接操作日历、文档与消息。","zhuanlan.zhihu.com","https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F2021337273094947061",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057899643-ocat.png","tools","en","adbb1b16-7897-40c9-81c2-e9d28f6ef3e4",[17,18,19,20,21],"飞书 CLI","AI Agent","Claude Code","Cursor","办公自动化",11,"2026-04-01T10:12:33.035279+00:00","2026-04-01T10:12:33.003+00:00",{"tags":26,"relatedLang":34,"relatedPosts":38},[27,29,31],{"name":20,"slug":28},"cursor",{"name":19,"slug":30},"claude-code",{"name":32,"slug":33},"AI agent","ai-agent",{"id":15,"slug":35,"title":36,"language":37},"feishu-open-source-cli-ai-agent-office-zh","飛書開源 CLI，讓 AI 直接管協作","zh",[39,45,51,57,63,69],{"id":40,"slug":41,"title":42,"cover_image":43,"image_url":43,"created_at":44,"category":13},"edbc7ba0-433a-41fe-8e18-d5420b0d7b4e","copilot-studio-2026-wave-planned-features-en","Copilot Studio’s 2026 wave turns planning into shipping","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782810210484-a8sa.png","2026-06-30T09:02:59.610853+00:00",{"id":46,"slug":47,"title":48,"cover_image":49,"image_url":49,"created_at":50,"category":13},"cce06058-c819-4d0f-83a0-98f77e88e471","deno-29-desktop-apps-runtime-bet-en","Deno 2.9 makes desktop apps a serious runtime bet","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782787666738-hfc1.png","2026-06-30T02:47:19.79177+00:00",{"id":52,"slug":53,"title":54,"cover_image":55,"image_url":55,"created_at":56,"category":13},"f1978cec-c46f-488b-8b25-deff15ba38bf","happyhorse-11-video-api-workflow-en","HappyHorse 1.1 turns video API chaos into a workflow","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782775996558-ffs5.png","2026-06-29T23:32:46.441611+00:00",{"id":58,"slug":59,"title":60,"cover_image":61,"image_url":61,"created_at":62,"category":13},"469d5667-8af3-4612-91e0-98a113f8deb0","sora-ai-2026-realistic-video-generation-guide-en","Sora AI in 2026: realistic video generation guide","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782774173362-kpwd.png","2026-06-29T23:02:21.735423+00:00",{"id":64,"slug":65,"title":66,"cover_image":67,"image_url":67,"created_at":68,"category":13},"b4c562fc-e04e-448c-83b4-d498c1306c62","pixelrag-screenshots-retrievable-context-en","PixelRAG turns screenshots into retrievable context","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782759806056-apni.png","2026-06-29T19:02:59.90502+00:00",{"id":70,"slug":71,"title":72,"cover_image":73,"image_url":73,"created_at":74,"category":13},"426e735b-aedc-45a9-bf1c-7e84ece9493e","codex-deepseek-v4-pro-moark-setup-en","Codex 接入 DeepSeek-V4-Pro，三步可用","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782738173484-wn38.png","2026-06-29T13:02:25.248526+00:00",[76,81,86,91,96,101,106,111,116,121],{"id":77,"slug":78,"title":79,"created_at":80},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":82,"slug":83,"title":84,"created_at":85},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":87,"slug":88,"title":89,"created_at":90},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":92,"slug":93,"title":94,"created_at":95},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":97,"slug":98,"title":99,"created_at":100},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":102,"slug":103,"title":104,"created_at":105},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":107,"slug":108,"title":109,"created_at":110},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":112,"slug":113,"title":114,"created_at":115},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":117,"slug":118,"title":119,"created_at":120},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":122,"slug":123,"title":124,"created_at":125},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]