[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASCYK5Y868XVHCS13HMJ4Q":3,"skill-same:01M7ASCYK5Y868XVHCS13HMJ4Q":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7ASCYK5Y868XVHCS13HMJ4Q","building-data-apps",null,"Build modern data apps, dashboards, and interactive reports using either\nReact + Vite or Streamlit. Includes optional Gemini Data Analytics chat\nintegration for an AI powered \"chat with your data\" experience.\n\nRelevant when any of the following conditions are true:\n  1. User explicitly requests to build a data dashboard, data application, or visualization UI, and the UI pulls data from a GCP database (defaulting to BigQuery unless otherwise specified).\n  2. You need to generate a frontend web application to interact with, query, and visualize data from GCP data sources.\n  3. User wants to build a \"chat with your data\" experience or integrate the Gemini Data Analytics chat API into a web interface.\n\nDo NOT use when any of the following conditions are true:\n  1. The request is for building backend-only services.\n  2. The request is for simple CLI scripts or command-line applications.\n  3. The web application is not data-centric or does not involve visualizing\u002Fquerying data from GCP sources.","saski\u002Farnesto","saski","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140356?v=4","01M7ASBDSNXTRYDYB4K1PEA1RV","01M7ASBDTAKBDAAV99S1GE7HK6",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: building-data-apps\ndescription: |\n  Build modern data apps, dashboards, and interactive reports using either\n  React + Vite or Streamlit. Includes optional Gemini Data Analytics chat\n  integration for an AI powered \"chat with your data\" experience.\n\n  Relevant when any of the following conditions are true:\n    1. User explicitly requests to build a data dashboard, data application, or visualization UI, and the UI pulls data from a GCP database (defaulting to BigQuery unless otherwise specified).\n    2. You need to generate a frontend web application to interact with, query, and visualize data from GCP data sources.\n    3. User wants to build a \"chat with your data\" experience or integrate the Gemini Data Analytics chat API into a web interface.\n\n  Do NOT use when any of the following conditions are true:\n    1. The request is for building backend-only services.\n    2. The request is for simple CLI scripts or command-line applications.\n    3. The web application is not data-centric or does not involve visualizing\u002Fquerying data from GCP sources.\nlicense: Apache-2.0\nmetadata:\n  version: v1\n  publisher: google\n---\n\n# Building Data Applications\n\nArchitect high-quality data dashboards and interactive reports. You MUST select\nthe appropriate framework before implementation.\n\n## Step 0: Framework Selection\n\nYou MUST select the framework based on the user's maintenance requirements and\ndata ecosystem.\n\n### Choice: Streamlit\n\n-   **User Profile**: Data Scientists \u002F Python users.\n-   **Logic Complexity**: High Python dependency (Pandas, NumPy, local data\n    processing).\n-   **Deployment**: Single-file Python script.\n-   **Customization**: Standard layout (fast boilerplate).\n\n### Choice: React + Vite\n\n-   **User Profile**: Web Developers \u002F Full-stack teams.\n-   **Logic Complexity**: High UI and Interactivity requirements (e.g.,\n    drag-and-drop, interactive maps).\n-   **Deployment**: Standalone Frontend + Backend API.\n-   **Customization**: Infinite (Custom CSS, specialized JS libraries).\n\n### Guidance:\n\n-   **Check for existing stack first**: ALWAYS prefer the framework the user is\n    already using in their project (e.g., if you see a `package.json` with React\n    dependencies, use React; if you see existing Streamlit files, use\n    Streamlit).\n-   **Default to React + Vite** for production-grade applications that require\n    complex client-side state, custom branding, or integration into a larger web\n    ecosystem.\n-   **Default to Streamlit** if the user specifically mentions \"Python\n    dashboard\", needs to iterate on complex local Python data processing, or\n    requires a single-script deployment.\n\n## Step 1: Implementation Plan\n\nYou MUST propose a plan to the user that specifies the chosen framework and\njustifies the choice based on the criteria above.\n\n--------------------------------------------------------------------------------\n\n## Shared Design Standards\n\nRegardless of framework, you MUST follow the principles in\n`resources\u002Fshared_design_system.md`.\n\n-   **Visual Style**: Minimal chrome, zinc color palette, and card-based\n    layouts.\n-   **Typography**: `DM Sans` for content, `JetBrains Mono` for data.\n\n--------------------------------------------------------------------------------\n\n## Framework Implementation\n\n### If using Streamlit:\n\n1.  Read `resources\u002Fstreamlit_framework.md` for detailed CSS and component\n    patterns.\n2.  Follow the \"Checklist for New Dashboards\" in that file.\n\n### If using React + Vite:\n\n1.  Read `resources\u002Freact_framework.md` for Tailwind and ECharts setup.\n2.  Follow the detailed component guidelines for KPI cards, Tables, and Panels.\n\n--------------------------------------------------------------------------------\n\n## AI Chat Interface (Optional Feature)\n\n```\n> [!IMPORTANT]\n>\n> If the user does not explicitly request a chat interface, you SHOULD\n> proactively ask them: \"Would you like to include a Gemini-powered chat\n> interface to enable natural language queries against your data?\" OR if\n> there is an implementation plan: \"Would you like to include a\n> Gemini-powered chat interface to enable natural language queries against\n> your data? Let me know and I'll update the plan!\".\n```\n\nIf the user requests or agrees to the chat interface:\n\n```\n> [!CAUTION]\n>\n> Adding the chat interface is a significant change. Implicit approval of\n> the implementation plan for including the chat interface MUST never be\n> assumed.\n```\n\n1.  **Gather Technical Details**: You MUST read `resources\u002Fchat_integration.md`\n    for the technical requirements.\n2.  **Update the implementation plan**: If and only if there is an\n    implementation plan, you MUST update the implementation plan. This is a\n    significant change so the user must explicitly approve the updated plan.\n3.  **Verify Prerequisites**: Ensure the user has the Gemini Data Analytics API\n    enabled and data exists in BigQuery.\n4.  **Reference Examples**: Adapt the patterns in\n    `examples\u002Freact_chat_panel.jsx` and either `examples\u002Ffastapi_chat.py` or\n    `examples\u002Fexpress_chat.ts`.\n\n## Acceptance Criteria\n\n> [!CAUTION]\n>\n> If available, you MUST use browser testing capabilities (such as\n> `browser_subagent`, Puppeteer, Playwright, or an equivalent available tool) to\n> visually verify the frontend application is working correctly *before*\n> notifying the user that the task is complete.\n\n> [!IMPORTANT]\n>\n> The following checklist represents the strict requirements for this task. You\n> must include these items in whatever format you use to track your work (e.g.,\n> your task list, implementation plan, or internal checklist).\n\n-   [ ] Are CSS hover transitions smooth?\n-   [ ] Are date fields formatted readably? (e.g., `MMM dd, yyyy`)\n-   [ ] Do z-indexes stack correctly so dropdowns appear above table headers?\n    (`relative z-30`)\n-   [ ] Do all interactive form\u002Fbutton inputs handle loading\u002Fdisabled states?\n-   [ ] Is the application responsive and does the layout adapt well to\n    different screen sizes?\n-   [ ] Are API calls for data fetching successful, and is there appropriate\n    error handling?\n-   [ ] Does the dark mode toggle function correctly and apply styles\n    consistently?\n-   [ ] Do all visualizations render correctly and are they interactive where\n    expected?\n-   [ ] Is the dashboard visually appealing?\n","# Building Data Applications\n\nArchitect high-quality data dashboards and interactive reports. You MUST select\nthe appropriate framework before implementation.\n\n## Step 0: Framework Selection\n\nYou MUST select the framework based on the user's maintenance requirements and\ndata ecosystem.\n\n### Choice: Streamlit\n\n-   **User Profile**: Data Scientists \u002F Python users.\n-   **Logic Complexity**: High Python dependency (Pandas, NumPy, local data\n    processing).\n-   **Deployment**: Single-file Python script.\n-   **Customization**: Standard layout (fast boilerplate).\n\n### Choice: React + Vite\n\n-   **User Profile**: Web Developers \u002F Full-stack teams.\n-   **Logic Complexity**: High UI and Interactivity requirements (e.g.,\n    drag-and-drop, interactive maps).\n-   **Deployment**: Standalone Frontend + Backend API.\n-   **Customization**: Infinite (Custom CSS, specialized JS libraries).\n\n### Guidance:\n\n-   **Check for existing stack first**: ALWAYS prefer the framework the user is\n    already using in their project (e.g., if you see a `package.json` with React\n    dependencies, use React; if you see existing Streamlit files, use\n    Streamlit).\n-   **Default to React + Vite** for production-grade applications that require\n    complex client-side state, custom branding, or integration into a larger web\n    ecosystem.\n-   **Default to Streamlit** if the user specifically mentions \"Python\n    dashboard\", needs to iterate on complex local Python data processing, or\n    requires a single-script deployment.\n\n## Step 1: Implementation Plan\n\nYou MUST propose a plan to the user that specifies the chosen framework and\njustifies the choice based on the criteria above.\n\n--------------------------------------------------------------------------------\n\n## Shared Design Standards\n\nRegardless of framework, you MUST follow the principles in\n`resources\u002Fshared_design_system.md`.\n\n-   **Visual Style**: Minimal chrome, zinc color palette, and card-based\n    layouts.\n-   **Typography**: `DM Sans` for content, `JetBrains Mono` for data.\n\n--------------------------------------------------------------------------------\n\n## Framework Implementation\n\n### If using Streamlit:\n\n1.  Read `resources\u002Fstreamlit_framework.md` for detailed CSS and component\n    patterns.\n2.  Follow the \"Checklist for New Dashboards\" in that file.\n\n### If using React + Vite:\n\n1.  Read `resources\u002Freact_framework.md` for Tailwind and ECharts setup.\n2.  Follow the detailed component guidelines for KPI cards, Tables, and Panels.\n\n--------------------------------------------------------------------------------\n\n## AI Chat Interface (Optional Feature)\n\n```\n> [!IMPORTANT]\n>\n> If the user does not explicitly request a chat interface, you SHOULD\n> proactively ask them: \"Would you like to include a Gemini-powered chat\n> interface to enable natural language queries against your data?\" OR if\n> there is an implementation plan: \"Would you like to include a\n> Gemini-powered chat interface to enable natural language queries against\n> your data? Let me know and I'll update the plan!\".\n```\n\nIf the user requests or agrees to the chat interface:\n\n```\n> [!CAUTION]\n>\n> Adding the chat interface is a significant change. Implicit approval of\n> the implementation plan for including the chat interface MUST never be\n> assumed.\n```\n\n1.  **Gather Technical Details**: You MUST read `resources\u002Fchat_integration.md`\n    for the technical requirements.\n2.  **Update the implementation plan**: If and only if there is an\n    implementation plan, you MUST update the implementation plan. This is a\n    significant change so the user must explicitly approve the updated plan.\n3.  **Verify Prerequisites**: Ensure the user has the Gemini Data Analytics API\n    enabled and data exists in BigQuery.\n4.  **Reference Examples**: Adapt the patterns in\n    `examples\u002Freact_chat_panel.jsx` and either `examples\u002Ffastapi_chat.py` or\n    `examples\u002Fexpress_chat.ts`.\n\n## Acceptance Criteria\n\n> [!CAUTION]\n>\n> If available, you MUST use browser testing capabilities (such as\n> `browser_subagent`, Puppeteer, Playwright, or an equivalent available tool) to\n> visually verify the frontend application is working correctly *before*\n> notifying the user that the task is complete.\n\n> [!IMPORTANT]\n>\n> The following checklist represents the strict requirements for this task. You\n> must include these items in whatever format you use to track your work (e.g.,\n> your task list, implementation plan, or internal checklist).\n\n-   [ ] Are CSS hover transitions smooth?\n-   [ ] Are date fields formatted readably? (e.g., `MMM dd, yyyy`)\n-   [ ] Do z-indexes stack correctly so dropdowns appear above table headers?\n    (`relative z-30`)\n-   [ ] Do all interactive form\u002Fbutton inputs handle loading\u002Fdisabled states?\n-   [ ] Is the application responsive and does the layout adapt well to\n    different screen sizes?\n-   [ ] Are API calls for data fetching successful, and is there appropriate\n    error handling?\n-   [ ] Does the dark mode toggle function correctly and apply styles\n    consistently?\n-   [ ] Do all visualizations render correctly and are they interactive where\n    expected?\n-   [ ] Is the dashboard visually appealing?\n",{"name":5,"license":14,"metadata":23,"description":26},{"version":24,"publisher":25},"v1","google","Build modern data apps, dashboards, and interactive reports using either\nReact + Vite or Streamlit. Includes optional Gemini Data Analytics chat\nintegration for an AI powered \"chat with your data\" experience.\n\nRelevant when any of the following conditions are true:\n  1. User explicitly requests to build a data dashboard, data application, or visualization UI, and the UI pulls data from a GCP database (defaulting to BigQuery unless otherwise specified).\n  2. You need to generate a frontend web application to interact with, query, and visualize data from GCP data sources.\n  3. User wants to build a \"chat with your data\" experience or integrate the Gemini Data Analytics chat API into a web interface.\n\nDo NOT use when any of the following conditions are true:\n  1. The request is for building backend-only services.\n  2. The request is for simple CLI scripts or command-line applications.\n  3. The web application is not data-centric or does not involve visualizing\u002Fquerying data from GCP sources.\n","main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Fbuilding-data-apps",0,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto","https:\u002F\u002Fgithub.com\u002Fsaski","http:\u002F\u002Fsaski.com","2026-11-12 20:09:16",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add saski\u002Farnesto --skill building-data-apps",{"tool":41,"command":42},"bunx","bunx skills add saski\u002Farnesto --skill building-data-apps",{"tool":44,"command":45},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill building-data-apps","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002FSKILL.md",true,[49,55,59,65,71,75,79],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"examples\u002Fexpress_chat.ts","SCRIPT","脚本",5108,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fexamples\u002Fexpress_chat.ts",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"examples\u002Ffastapi_chat.py",4774,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fexamples\u002Ffastapi_chat.py",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"examples\u002Freact_chat_panel.jsx","OTHER","其他",11937,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fexamples\u002Freact_chat_panel.jsx",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"resources\u002Fchat_integration.md","REFERENCE","参考文档",4389,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fresources\u002Fchat_integration.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"resources\u002Freact_framework.md",10348,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fresources\u002Freact_framework.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"resources\u002Fshared_design_system.md",1158,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fresources\u002Fshared_design_system.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"resources\u002Fstreamlit_framework.md",8491,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbuilding-data-apps\u002Fresources\u002Fstreamlit_framework.md",[84,92,99,106,113,120],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7AT7F5FSHNAMFMF01N0QA1X","visualize","Use \u002Fvisualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.","Unlicense","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fvisualize\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7AT79MHSAR3JDDMP7DGERM9","update-cursor-settings","Modify Cursor\u002FVSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cursor-settings\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M7AT73WF3Y22E0FKYAMCCJES","update-cli-config","View and modify Cursor CLI configuration settings in ~\u002F.cursor\u002Fcli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cli-config\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M7AT6F3FBP85AJJ5BJNR8B5W","statusline","Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fstatusline\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":18},"01M7AT6D24QFS5XRAFN8S5XJ7W","split-to-prs","Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fsplit-to-prs\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":18},"01M7AT69FYFN84XZKW452JV5DF","shell","Runs the rest of a \u002Fshell request as a literal shell command. Use only when the user explicitly invokes \u002Fshell and wants the following text executed directly in the terminal.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fshell\u002FSKILL.md",[],[]]