[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-workbuddy-jineng-mcp-zhuanjia-qubie-zh":3,"article-related-workbuddy-jineng-mcp-zhuanjia-qubie-zh":32,"series-industry-f5cf0685-7490-43ec-be14-71be76a0270b":77},{"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":25,"views":29,"created_at":30,"published_at":31,"topic_cluster_id":11},"f5cf0685-7490-43ec-be14-71be76a0270b","workbuddy-jineng-mcp-zhuanjia-qubie-zh","WorkBuddy 里技能、MCP、专家怎么分工","\u003Cp>WorkBuddy 里的“技能”、\u003Ca href=\"\u002Ftag\u002Fmcp\">MCP\u003C\u002Fa> 和“专家”到底怎么分工？\u003C\u002Fp>\u003Cp data-speakable=\"summary\">技能管执行方式，专家管角色分工，MCP 管外部连接。\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>项目\u003C\u002Fth>\u003Cth>定位\u003C\u002Fth>\u003Cth>主要作用\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>专家\u003C\u002Ftd>\u003Ctd>角色层\u003C\u002Ftd>\u003Ctd>决定谁来干活\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>技能\u003C\u002Ftd>\u003Ctd>能力层\u003C\u002Ftd>\u003Ctd>决定怎么干得专业\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>MCP\u003C\u002Ftd>\u003Ctd>连接层\u003C\u002Ftd>\u003Ctd>决定从哪拿外部工具和数据\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>1. 先把三者放到同一张图里\u003C\u002Fh2>\u003Cp>这份清单看完，你就能判断一项任务该先配角色、补能力，还是先接数据源。对做文档、表格、知识库或数据库\u003Ca href=\"\u002Fnews\u002Fchatgpt-mac-computer-history-memory-zh\">工作\u003C\u002Fa>的人来说，分清这三层，往往比盲目加功能更有效。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786824176035-4j5r.png\" alt=\"WorkBuddy 里技能、MCP、专家怎么分工\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>最实用的理解方式是：专家决定“谁来干活”，技能决定“怎么干得专业”，MCP 负责“连外部\u003Ca href=\"\u002Fnews\u002Fdeepseek-plugin-harness-turns-agents-into-tools-zh\">工具\u003C\u002Fa>和数据”。这不是三选一，而是三层分工。\u003C\u002Fp>\u003Cul>\u003Cli>专家：适合定义任务角色，比如数据分析、写作、客服\u003C\u002Fli>\u003Cli>技能：适合补强具体动作，比如 xlsx 处理、表格清洗、摘要生成\u003C\u002Fli>\u003Cli>MCP：适合接入外部资源，比如网盘、数据库、内部系统\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>2. 专家：决定“谁来干活”\u003C\u002Fh2>\u003Cp>专家更像岗位模板。你不会让通用助手硬猜所有问题，而是让它切到更贴近任务的角色。比如“数据分析专家”会更关注指标、异常、口径和结论表达；“写作专家”会更关注结构、语气和受众。\u003C\u002Fp>\u003Cp>它的价值是减少上下文切换。先选对角色，再让它处理对应类型的任务，通常比一上来就让通用模型硬做更稳定。\u003C\u002Fp>\u003Cul>\u003Cli>适合：固定类型任务、重复性工作、需要统一口径的团队\u003C\u002Fli>\u003Cli>不适合：一次性很零散、没有明确角色边界的任务\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>3. 技能：决定“怎么干得专业”\u003C\u002Fh2>\u003Cp>技能是更细的一层，它不是角色，而是能力模块。比如 xlsx 技能可以专门处理 Excel 文件，帮助模型更好地读表、改表、总结表格内容。它解决的是“做法”问题，而不是“身份”问题。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786824174886-qfp7.png\" alt=\"WorkBuddy 里技能、MCP、专家怎么分工\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>如果把专家比作岗位，技能就像岗位上的专业工具。一个写作专家可以叠加摘要技能、改写技能、表格提取技能，让输出更贴近实际办公需求。\u003C\u002Fp>\u003Ccode>专家 = 角色选择\u003Cbr>技能 = 专业动作\u003Cbr>示例：数据分析专家 + xlsx 技能\u003C\u002Fcode>\u003Ch2>4. MCP：负责连接外部工具和数据\u003C\u002Fh2>\u003Cp>MCP 的作用不在“会不会分析”，而在“能不能拿到数据”。它更像连接器，让 WorkBuddy 去访问数据库、网盘、内部系统或其他外部服务。没有 MCP，模型可能只能基于你贴进去的内容回答；有了 MCP，它才能直接读到外部数据源。\u003C\u002Fp>\u003Cp>这也是为什么 MCP 和技能不冲突。技能解决方法，MCP 解决输入来源。办公里常见的组合不是二选一，而是“先连数据，再用技能处理，再交给专家角色输出”。\u003C\u002Fp>\u003Cul>\u003Cli>可连接：数据库、网盘、业务系统、知识库\u003C\u002Fli>\u003Cli>适合场景：查数据、取文件、跨系统汇总信息\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>5. 它们为什么可以叠着用\u003C\u002Fh2>\u003Cp>三者是不同层面的东西，可以叠着用。这意味着你不需要纠结“到底选技能还是选 MCP”，因为它们本来就不是同一维度。一个实际任务里，往往会同时用到专家、技能和 MCP。\u003C\u002Fp>\u003Cp>比如你要做月报：先用 MCP 拉取数据库里的销售数据，再用 xlsx 技能整理表格，最后交给数据分析专家生成结论和建议。这个组合比单独靠一个通用助手更贴近真实办公\u003Ca href=\"\u002Fnews\u002Fanthropic-watermark-copy-paste-dev-workflow-zh\">流程\u003C\u002Fa>。\u003C\u002Fp>\u003Cul>\u003Cli>组合示例 1：数据分析专家 + xlsx 技能 + 数据库 MCP\u003C\u002Fli>\u003Cli>组合示例 2：写作专家 + 摘要技能 + 网盘 MCP\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>6. 15 个技能为什么值得看\u003C\u002Fh2>\u003Cp>标题说的是“最值得推荐的 15 个技能”，但从这段内容能看出的重点并不是数量，而是分类思路。你真正要找的，不是“技能越多越好”，而是哪些技能能补上你日常工作里最常见的动作缺口。\u003C\u002Fp>\u003Cp>如果你经常处理表格、文档、资料整理和跨系统信息汇总，那么技能列表的意义就在于：它让 WorkBuddy 不只是聊天，而是更像一个可以按任务配置的办公助手。\u003C\u002Fp>\u003Cul>\u003Cli>优先看：表格处理、文档整理、摘要、改写\u003C\u002Fli>\u003Cli>其次看：和你现有数据源能否配合使用\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>哪种适合你\u003C\u002Fh2>\u003Cp>如果你在搭建稳定的办公流程，先选专家，再补技能，最后按需要接 MCP。这样最容易把“谁来做”“怎么做”“从哪取数据”分开管理。\u003C\u002Fp>\u003Cp>如果你的任务主要是读表、写报告、整理知识库，那就优先关注技能；如果你的任务依赖实时数据或内部系统，就先看 MCP；如果你要统一团队输出风格，就先定专家角色。\u003C\u002Fp>","3 类能力分工清楚：专家管谁干活，技能管怎么干，MCP 管外部连接。看完就能决定先配角色、补能力，还是接数据源。","zhuanlan.zhihu.com","https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F2071511412988437241",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786824176035-4j5r.png","industry","zh","e8b7f93d-f815-479d-b7e2-c30641d861c8",[17,18,19,20,21,22,23,24],"WorkBuddy","MCP","技能","专家","办公助手","xlsx","数据分析","工作流",[26,27,28],"专家管角色分工，技能管具体执行，MCP 管外部连接","三者不是互斥关系，实际任务里通常会叠着用","先看任务类型：统一口径选专家，补动作选技能，接数据选 MCP",0,"2026-08-15T20:02:29.690908+00:00","2026-08-15T20:02:29.659+00:00",{"tags":33,"relatedLang":36,"relatedPosts":40},[34],{"name":18,"slug":35},"mcp",{"id":15,"slug":37,"title":38,"language":39},"workbuddy-skills-office-work-picks-en","WorkBuddy Skills: 5 picks that fit real office work","en",[41,47,53,59,65,71],{"id":42,"slug":43,"title":44,"cover_image":45,"image_url":45,"created_at":46,"category":13},"54ada8df-3058-4dd1-94ef-e7e78f611e22","glm-5-3-coding-gains-post-training-zh","GLM-5.3 編碼提升，重點在後訓練","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786773771566-dghc.png","2026-08-15T06:02:18.29616+00:00",{"id":48,"slug":49,"title":50,"cover_image":51,"image_url":51,"created_at":52,"category":13},"26c83d04-4b98-4e82-95f0-1e94e19d2c92","anthropic-data-center-push-big-capital-backing-zh","Anthropic 50 億美元數據中心背後的 5 個資本動作","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786752165620-j8sc.png","2026-08-15T00:02:21.073927+00:00",{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":13},"057e9280-7f45-499f-85c7-bd678f90c812","dailyarxiv-arxiv-keyword-paper-feed-zh","DailyArxiv 把 arXiv 關鍵字變成每日論文流","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786716168076-7w4o.png","2026-08-14T14:02:22.664653+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":13},"1ffd9308-dd6c-4aed-8cc2-91587d8e72a9","claude-vs-chatgpt-2026-claude-bi-jiao-qiang-ma-zh","Claude vs ChatGPT（2026）：Claude 比較強嗎？","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786710773369-l0tu.png","2026-08-14T12:32:29.306266+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":13},"5680d9ca-166f-4269-82fe-91146cf9ed13","cbdc-governance-standards-stakeholder-roles-zh","CBDC 治理看誰管、誰負責","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786672975574-0kxc.png","2026-08-14T02:02:29.052638+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":13},"46216108-15ba-40ae-811b-ecb63ecb5c7d","invisible-ai-watermarks-right-move-claude-zh","Claude 的無形 AI 水印是對的選擇","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786665770533-24wm.png","2026-08-14T00:02:27.653275+00:00",[78,83,88,93,98,103,108,113,118,123],{"id":79,"slug":80,"title":81,"created_at":82},"ee073da7-28b3-4752-a319-5a501459fb87","ai-in-2026-what-actually-matters-now-zh","2026 AI 真正重要的事","2026-03-26T07:09:12.008134+00:00",{"id":84,"slug":85,"title":86,"created_at":87},"83bd1795-8548-44c9-9a7e-de50a0923f71","trump-ai-framework-power-speech-state-preemption-zh","川普 AI 框架瞄準電力、言論與州權","2026-03-26T07:12:18.695466+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"ea6be18b-c903-4e54-97b7-5f7447a612e0","nvidia-gtc-2026-big-ai-announcements-zh","NVIDIA GTC 2026 重點拆解","2026-03-26T07:14:26.62638+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"4bcec76f-4c36-4daa-909f-54cd702f7c93","claude-users-spreading-out-and-getting-better-zh","Claude 用戶更分散，也更會用","2026-03-26T07:22:52.325888+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"bd903b15-2473-4178-9789-b7557816e535","openclaw-raises-hard-question-for-ai-models-zh","OpenClaw 逼問 AI 模型價值","2026-03-26T07:24:54.707486+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"eeac6b9e-ad9d-4831-8eec-8bba3f9bca6a","gap-google-gemini-checkout-fashion-search-zh","Gap 把結帳搬進 Gemini","2026-03-26T07:28:23.937768+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"0740e53f-605d-4d57-8601-c10beb126f3c","google-pushes-gemini-transition-to-march-2026-zh","Google 把 Gemini 轉換延到 2026 年 3…","2026-03-26T07:30:12.825269+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"e660d801-2421-4529-8fa9-86b82b066990","metas-llama-4-benchmark-scandal-gets-worse-zh","Meta Llama 4 分數風波又擴大","2026-03-26T07:34:21.156421+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"183f9e7c-e143-40bb-a6d5-67ba84a3a8bc","accenture-mistral-ai-sovereign-enterprise-deal-zh","Accenture 攜手 Mistral AI 賣主權 AI","2026-03-26T07:38:14.818906+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"191d9b1b-768a-478c-978c-dd7431a38149","mistral-ai-faces-its-hardest-year-yet-zh","Mistral AI 迎來最硬的一年","2026-03-26T07:40:23.716374+00:00"]