[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tb-a-2077776803493052416-2077777907689717760":3},{"detail":4,"html":18,"toc":19,"catalog":32,"tool":36},{"id":5,"title":6,"coverUrl":7,"url":8,"level":8,"description":9,"publishDate":10,"views":11,"isCollect":12,"isLike":12,"vipRequired":13,"vipFlag":14,"price":8,"contentType":15,"station":8,"seq":15,"readMinutes":16,"toolIds":17,"relatedVideo":8},"2077777907689717760","Anthropic 数据分析套件：探索→SQL→分析→图表→仪表盘一条龙","",null,"Anthropic 官方数据分析插件，把 Claude 变成数据分析师。六个命令一条流水线：explore-data 摸清数据→write-query 写优化 SQL→analyze 答问题→create-viz 出版级图表→build-dashboard 交互式看板→validate 交付前 QA。连数仓（Snowflake\u002FBigQuery 等）直查，没连也能传 CSV\u002FExcel。边界：为 Cowork 设计，也支持 Claude Code，直连数仓需自备 MCP。","2026-07-16",0,"0",false,"1",1,3,[],"\u003Cdiv style=\"padding:0 4px 24px;font-size:14px;color:#333;line-height:1.85;word-break:break-word\">\n\n\u003Cdiv style=\"background:#FFF7ED;border:1px solid #FFEDD5;border-radius:12px;padding:14px;margin:0 0 18px;font-size:13px;line-height:1.7;color:#9A3412\">🏛️ \u003Cstrong style=\"font-weight:700;color:#EA580C\">官方旗舰\u003C\u002Fstrong>：Anthropic 官方数据分析插件，一张卡覆盖\u003Cstrong style=\"font-weight:700;color:#EA580C\">「探索→查询→分析→可视化→仪表盘→质检」全流程\u003C\u002Fstrong>。这一条是数据分析类目的主力。\u003C\u002Fdiv>\n\n\u003Ch1 style=\"font-size:17px;font-weight:800;color:#111;margin:26px 0 14px;padding-left:10px;border-left:5px solid #FF8916;line-height:1.5\" id=\"s1\" data-toc>一、它把 Claude 变成一个数据分析师\u003C\u002Fh1>\n\u003Cp style=\"margin:0 0 14px\">不是单个小工具，而是一整套\u003Cstrong style=\"font-weight:700;color:#1a1a1a\">数据分析工作流\u003C\u002Fstrong>：帮你摸清数据集、写优化 SQL、建可视化、做交互式仪表盘，交付给老板\u002F客户前还帮你 QA 一遍。适配任意数据仓库、任意 SQL 方言、任意分析栈。\u003C\u002Fp>\n\n\u003Ch1 style=\"font-size:17px;font-weight:800;color:#111;margin:26px 0 14px;padding-left:10px;border-left:5px solid #FF8916;line-height:1.5\" id=\"s2\" data-toc>二、六个命令 = 一条完整流水线\u003C\u002Fh1>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">1\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fexplore-data\u003C\u002Fcode> 摸清一个数据集的形态、质量、规律（多少行多少列、哪列有空值、哪列有异常值）\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">2\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fwrite-query\u003C\u002Fcode> 按你的 SQL 方言写优化查询，带最佳实践和性能优化\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">3\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fanalyze\u003C\u002Fcode> 回答数据问题——从快速查数到完整分析都行\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">4\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fcreate-viz\u003C\u002Fcode> 用 Python 出\u003Cstrong style=\"font-weight:700;color:#1a1a1a\">出版级图表\u003C\u002Fstrong>（自动选图型、讲设计原则）\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">5\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fbuild-dashboard\u003C\u002Fcode> 建带筛选器和图表的\u003Cstrong style=\"font-weight:700;color:#1a1a1a\">交互式 HTML 仪表盘\u003C\u002Fstrong>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#FAFAFA;border-radius:12px;padding:14px;margin:0 0 12px\">\u003Cdiv style=\"display:flex\">\u003Cspan style=\"background:#FF8916;color:#fff;width:22px;height:22px;border-radius:50%;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center;flex-shrink:0;margin-right:10px\">6\u003C\u002Fspan>\u003Cdiv style=\"flex:1\">\u003Ccode style=\"background:#F1F5F9;color:#EA580C;padding:1px 6px;border-radius:4px;font-size:13px\">\u002Fvalidate\u003C\u002Fcode> 交付前 QA：方法论、准确性、偏差三重检查\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\n\n\u003Ch1 style=\"font-size:17px;font-weight:800;color:#111;margin:26px 0 14px;padding-left:10px;border-left:5px solid #FF8916;line-height:1.5\" id=\"s3\" data-toc>三、有没有数据仓库都能用\u003C\u002Fh1>\n\u003Cdiv style=\"background:#fff;border:1px solid #F1F5F9;border-radius:14px;padding:14px;margin:0 0 10px;box-shadow:0 2px 10px rgba(0,0,0,0.03)\">\u003Cstrong style=\"font-weight:700;color:#EA580C\">连了数仓（最爽）\u003C\u002Fstrong>\u003Cdiv style=\"margin-top:4px\">接上 Snowflake \u002F Databricks \u002F BigQuery 等的 MCP 后，它直查你的库、摸清表结构、端到端跑分析、按结果迭代查询，全程不用复制粘贴。\u003C\u002Fdiv>\u003C\u002Fdiv>\n\u003Cdiv style=\"background:#fff;border:1px solid #F1F5F9;border-radius:14px;padding:14px;margin:0 0 10px;box-shadow:0 2px 10px rgba(0,0,0,0.03)\">\u003Cstrong style=\"font-weight:700;color:#EA580C\">没连数仓（照样能用）\u003C\u002Fstrong>\u003Cdiv style=\"margin-top:4px\">贴 SQL 查询结果、或直接上传 CSV\u002FExcel，它一样分析、出图；也能先帮你写好 SQL 让你自己跑，再分析你贴回来的结果。\u003C\u002Fdiv>\u003C\u002Fdiv>\n\n\u003Ch1 style=\"font-size:17px;font-weight:800;color:#111;margin:26px 0 14px;padding-left:10px;border-left:5px solid #FF8916;line-height:1.5\" id=\"s4\" data-toc>四、边界（诚实说明）\u003C\u002Fh1>\n\u003Cdiv style=\"background:#FFF7ED;border:1px solid #FFEDD5;border-radius:12px;padding:12px 14px;margin:0 0 16px;font-size:13px;line-height:1.7;color:#9A3412\">⚠️ 它主要为 Anthropic 桌面版 \u003Cstrong style=\"font-weight:700;color:#EA580C\">Cowork\u003C\u002Fstrong> 设计，也支持 Claude Code。想让它直连数据仓库直查，需要你自己先配好对应的 MCP 服务器；没有 MCP 就走\"贴结果\u002F传文件\"的路子，功能不打折但少了自动直查。\u003C\u002Fdiv>\n\n\u003Cdiv style=\"background:#F8FAFC;border-left:3px solid #CBD5E1;border-radius:6px;padding:10px 14px;margin:0 0 16px;font-size:13px;line-height:1.7;color:#475569\">跟本类目其它工具的分工：要的是\u003Cstrong style=\"font-weight:700;color:#475569\">规整 Excel 交付物\u003C\u002Fstrong>→ 官方 xlsx；要\u003Cstrong style=\"font-weight:700;color:#475569\">代码级批量数据处理\u003C\u002Fstrong>→ pandas；要\u003Cstrong style=\"font-weight:700;color:#475569\">端到端分析+看板\u003C\u002Fstrong>→ 就是本套件。\u003C\u002Fdiv>\n\n\u003C\u002Fdiv>\n",[20,23,26,29],{"id":21,"text":22,"level":15},"s1","一、它把 Claude 变成一个数据分析师",{"id":24,"text":25,"level":15},"s2","二、六个命令 = 一条完整流水线",{"id":27,"text":28,"level":15},"s3","三、有没有数据仓库都能用",{"id":30,"text":31,"level":15},"s4","四、边界（诚实说明）",[33],{"id":5,"title":6,"coverUrl":7,"duration":8,"level":8,"publishDate":10,"views":11,"aiSoftapp":8,"tags":34,"contentType":15,"station":8,"seq":15,"relateId":8,"toolId":35,"readMinutes":16},[],"2077776803493052416",{"id":35,"createTime":37,"createdBy":38,"updateTime":37,"updatedBy":38,"echoMap":39,"slug":40,"name":41,"categorySlug":42,"subCategory":43,"region":8,"website":44,"appName":7,"description":45,"tags":46,"sortOrder":11,"state":15,"tenantCode":52,"tutorialContent":8,"resourceType":53,"accessTypes":7,"installCmd":54,"logo":55,"hotScore":56,"githubStars":11,"category":42},"2026-07-16 23:26:08","1744248479271616512",{},"anthropic-data-analyst-suite","Anthropic 数据分析套件","data","数据分析与可视化","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002Fmain\u002Fdata","Anthropic 官方数据分析套件（knowledge-work-plugins\u002Fdata），把 Claude 变成你的数据分析搭子。一条龙：\u002Fexplore-data 摸清数据集形态与质量 → \u002Fwrite-query 按你的 SQL 方言写优化查询 → \u002Fanalyze 回答数据问题 → \u002Fcreate-viz 出版级图表 → \u002Fbuild-dashboard 交互式 HTML 仪表盘 → \u002Fvalidate 交付前做方法论\u002F准确性\u002F偏差 QA。连上数仓（Snowflake\u002FDatabricks\u002FBigQuery 等）可直查；没连也能贴 SQL 结果或传 CSV\u002FExcel 让它分析。边界：主要为 Anthropic 桌面版 Cowork 设计，也支持 Claude Code；直连数仓需自备 MCP。",[47,48,49,50,51],"官方·Anthropic出品","SQL→分析→可视化→仪表盘","全流程旗舰","接任意数仓","交付前QA","0000","skill","claude plugins add knowledge-work-plugins\u002Fdata","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4",90]