[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6991ZTBAGT71YK8FYA4RKVT":3,"skill-same:01M6991ZTBAGT71YK8FYA4RKVT":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6991ZTBAGT71YK8FYA4RKVT","meridian-result-visualization",null,"Loads a fitted Meridian model and generates standard visualization reports: Model Results Summary. Use when the user wants to load a saved model and view results (model performance, fit, health). Don't use for running budget optimization (use meridian-budget-optimization) or building\u002Ffitting the model (use meridian-model-building).","google\u002Fmeridian","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M6991Q88XBX9SPK8Y92MAEWF",1605,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_result_visualization\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"meridian","visualization","result","meridian result visualization","reports","running","when","standard","for","load","saved","loads","fit","use","results","view","model","health","Optimization","performance","2026-11-10 10:12:30",false,"---\nname: meridian-result-visualization\ndescription: >-\n  Loads a fitted Meridian model and generates standard visualization reports:\n  Model Results Summary.\n  Use when the user wants to load a saved model and view results (model performance, fit, health).\n  Don't use for running budget optimization (use meridian-budget-optimization) or building\u002Ffitting the model (use meridian-model-building).\n---\n\n# Meridian Result Visualization\n\nA skill for loading a fitted Meridian model and generating standard\nvisualization reports.\n\n## Core Workflow\n\n### Interactivity Checkpoint Rule\n\nThroughout this workflow, you will encounter **CRITICAL INTERACTIVE\nCHECKPOINT**s. At each checkpoint, you MUST:\n\n1.  Present the current proposed configurations, report paths, script path, or\n    status to the user for approval.\n2.  Ask the user if they are ready to proceed using the available\n    user-interaction tool (e.g., `ask_question`), structured as a\n    multiple-choice question. Do NOT use raw chat text.\n3.  Wait for their response before proceeding.\n    *   *MANDATORY*: You MUST pause at every checkpoint regardless of the\n        initial prompt instructions (even if the user request contains phrases\n        like \"run autonomously\", \"execute directly\", \"fix autonomously\", etc.).\n        The initial request does NOT bypass these interactive checkpoints.\n    *   *Note*: If the user replies to a checkpoint with a generic approval\n        (e.g., \"proceed\", \"do what you think is best\"), proceed with the\n        proposed defaults.\n\n--------------------------------------------------------------------------------\n\n### 1. Initial Setup\n\n*   Prompt the user for the path to the serialized model file\n    (`meridian_model.binpb` by default).\n*   Prompt the user for output paths for:\n    *   Model Results Summary report (`results_summary.html` by default).\n*   Prompt the user for the desired path for the generated Python script.\n*   Prompt the user for any optional configuration for the reports (e.g., date\n    ranges for results summary).\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the gathered paths and\n    configurations to the user and obtain confirmation before loading the model.\n\n### 2. Add Model Loading Code\n\n*   Use `meridian_serde.load_meridian()` to load the model.\n*   See [load_model.md](references\u002Fload_model.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the model load path\n    configuration and proposed Python code snippet to the user, and obtain\n    approval before continuing to specify health checks.\n\n### 3. Add Post-Modeling Health Checks Code (Optional)\n\n*   Use `reviewer.ModelReviewer` to run health checks and save to HTML.\n*   *Small \u002F Test Models*: If a model has fewer than 2 MCMC draws (e.g. test or\n    mock models where R-hat computation requires >= 2 samples), catch\n    `ValueError` or skip R-hat calculation gracefully so health check reports\n    generate cleanly.\n*   See [health_check.md](references\u002Fhealth_check.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the proposed health check\n    report path and code snippet to the user, and obtain approval before\n    continuing to results summary configuration.\n\n### 4. Add Model Results Summary Code\n\n*   Use `summarizer.Summarizer` to generate the HTML results summary, applying\n    any user-specified configuration (e.g., date ranges).\n    *   *Date Range Auto-Clipping*: If applying a user-specified date range\n        falls outside the model's time coordinates, clip or adjust the date\n        range to match the model's actual coordinates.\n    *   *Tip for errors*: If you encounter errors regarding `sample_prior`,\n        bypass or fix the requirement (for example, by setting\n        `sample_prior=False` or passing the required parameters) to ensure\n        successful generation.\n*   See [results_summary.md](references\u002Fresults_summary.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the proposed date ranges,\n    output path configuration, and code snippet for the results summary to the\n    user, and obtain approval before proceeding to script generation and\n    execution.\n\n### 5. Pre-execution Checkpoint\n\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the final report path and\n    script path to the user, and ask for final confirmation to execute the\n    results generation script now.\n\n### 6. Execution & Script Setup\n\n*   Write the accumulated Python script to the user-specified path. If your\n    file-writing tool can ask the user to review the written file, don't request\n    that review: the pre-execution checkpoint already asks for approval, and an\n    extra prompt pauses the workflow.\n*   Execute the script with the Python interpreter of the environment where\n    `google-meridian` is installed: the one the user named; else `python3` if a\n    virtual environment is already active (`VIRTUAL_ENV` or `CONDA_PREFIX` is\n    set); else the project directory's virtual environment (`.venv\u002F` or `venv\u002F`,\n    e.g., `.venv\u002Fbin\u002Fpython3`) if there is one; else `python3`. If `import\n    meridian` fails, ask the user which environment to use instead of searching\n    the machine or installing packages unprompted.\n*   **CRITICAL**: Do **NOT** delete the generated reports, the script, or the\n    output directory at the end of the task. These are the deliverables\n    requested by the user and must be preserved.\n","# Meridian Result Visualization\n\nA skill for loading a fitted Meridian model and generating standard\nvisualization reports.\n\n## Core Workflow\n\n### Interactivity Checkpoint Rule\n\nThroughout this workflow, you will encounter **CRITICAL INTERACTIVE\nCHECKPOINT**s. At each checkpoint, you MUST:\n\n1.  Present the current proposed configurations, report paths, script path, or\n    status to the user for approval.\n2.  Ask the user if they are ready to proceed using the available\n    user-interaction tool (e.g., `ask_question`), structured as a\n    multiple-choice question. Do NOT use raw chat text.\n3.  Wait for their response before proceeding.\n    *   *MANDATORY*: You MUST pause at every checkpoint regardless of the\n        initial prompt instructions (even if the user request contains phrases\n        like \"run autonomously\", \"execute directly\", \"fix autonomously\", etc.).\n        The initial request does NOT bypass these interactive checkpoints.\n    *   *Note*: If the user replies to a checkpoint with a generic approval\n        (e.g., \"proceed\", \"do what you think is best\"), proceed with the\n        proposed defaults.\n\n--------------------------------------------------------------------------------\n\n### 1. Initial Setup\n\n*   Prompt the user for the path to the serialized model file\n    (`meridian_model.binpb` by default).\n*   Prompt the user for output paths for:\n    *   Model Results Summary report (`results_summary.html` by default).\n*   Prompt the user for the desired path for the generated Python script.\n*   Prompt the user for any optional configuration for the reports (e.g., date\n    ranges for results summary).\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the gathered paths and\n    configurations to the user and obtain confirmation before loading the model.\n\n### 2. Add Model Loading Code\n\n*   Use `meridian_serde.load_meridian()` to load the model.\n*   See [load_model.md](references\u002Fload_model.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the model load path\n    configuration and proposed Python code snippet to the user, and obtain\n    approval before continuing to specify health checks.\n\n### 3. Add Post-Modeling Health Checks Code (Optional)\n\n*   Use `reviewer.ModelReviewer` to run health checks and save to HTML.\n*   *Small \u002F Test Models*: If a model has fewer than 2 MCMC draws (e.g. test or\n    mock models where R-hat computation requires >= 2 samples), catch\n    `ValueError` or skip R-hat calculation gracefully so health check reports\n    generate cleanly.\n*   See [health_check.md](references\u002Fhealth_check.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the proposed health check\n    report path and code snippet to the user, and obtain approval before\n    continuing to results summary configuration.\n\n### 4. Add Model Results Summary Code\n\n*   Use `summarizer.Summarizer` to generate the HTML results summary, applying\n    any user-specified configuration (e.g., date ranges).\n    *   *Date Range Auto-Clipping*: If applying a user-specified date range\n        falls outside the model's time coordinates, clip or adjust the date\n        range to match the model's actual coordinates.\n    *   *Tip for errors*: If you encounter errors regarding `sample_prior`,\n        bypass or fix the requirement (for example, by setting\n        `sample_prior=False` or passing the required parameters) to ensure\n        successful generation.\n*   See [results_summary.md](references\u002Fresults_summary.md) for code template.\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the proposed date ranges,\n    output path configuration, and code snippet for the results summary to the\n    user, and obtain approval before proceeding to script generation and\n    execution.\n\n### 5. Pre-execution Checkpoint\n\n*   **CRITICAL INTERACTIVE CHECKPOINT**: Present the final report path and\n    script path to the user, and ask for final confirmation to execute the\n    results generation script now.\n\n### 6. Execution & Script Setup\n\n*   Write the accumulated Python script to the user-specified path. If your\n    file-writing tool can ask the user to review the written file, don't request\n    that review: the pre-execution checkpoint already asks for approval, and an\n    extra prompt pauses the workflow.\n*   Execute the script with the Python interpreter of the environment where\n    `google-meridian` is installed: the one the user named; else `python3` if a\n    virtual environment is already active (`VIRTUAL_ENV` or `CONDA_PREFIX` is\n    set); else the project directory's virtual environment (`.venv\u002F` or `venv\u002F`,\n    e.g., `.venv\u002Fbin\u002Fpython3`) if there is one; else `python3`. If `import\n    meridian` fails, ask the user which environment to use instead of searching\n    the machine or installing packages unprompted.\n*   **CRITICAL**: Do **NOT** delete the generated reports, the script, or the\n    output directory at the end of the task. These are the deliverables\n    requested by the user and must be preserved.\n",{"name":5,"description":7},"main","271d6c9316f160090adcfe2e4b73dcce78a3edb0","skills\u002Fmeridian_result_visualization",312,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian","https:\u002F\u002Fdevelopers.google.com\u002Fmeridian","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 11:56:01",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add google\u002Fmeridian --skill meridian-result-visualization",{"tool":65,"command":66},"bunx","bunx skills add google\u002Fmeridian --skill meridian-result-visualization",{"tool":68,"command":69},"pnpm","pnpm dlx skills add google\u002Fmeridian --skill meridian-result-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_result_visualization\u002FSKILL.md",true,[73,79,83],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fhealth_check.md","REFERENCE","参考文档",482,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_result_visualization\u002Freferences\u002Fhealth_check.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fload_model.md",461,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_result_visualization\u002Freferences\u002Fload_model.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fresults_summary.md",391,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_result_visualization\u002Freferences\u002Fresults_summary.md",[88,111,129,148],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":100,"publishedAt":44},"01M6992184V3ZDYFMX8R0Z2226","meridian-scenario-planner","Generates Scenario Planner data from a fitted Meridian model and exports it for Looker Studio dashboard creation via Colab handoff. Use when the user wants to generate scenario planning data, budget grids, or Looker Studio dashboards from a saved model. Don't use for visualizing model results (use meridian-result-visualization) or running standard budget optimization (use meridian-budget-optimization).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_scenario_planner\u002FSKILL.md",[94,95],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[101,24,102,103,104,37,29,30,31,32,34,105,106,107,38,40,42,108,25,109,110],"scenario planner","planner","meridian scenario planner","scenario","studio","via","creation","planning","dashboard","handoff",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":118,"publishedAt":44},"01M6991WWEVPXCQREVNT95VP64","meridian-model-building","Guides users through building a Meridian Marketing Mix Modeling (MMM) model. Use when a user wants to load data, map columns, configure ModelSpec, run Exploratory Data Analysis (EDA), fit a model, and save the model. Don't use for visualizing results or creating a scenario planner.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_model_building\u002FSKILL.md",[117],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,24,40,120,121,33,32,101,122,123,36,124,37,38,102,125,30,126,127,128],"meridian model building","mix","map","users","guides","configure","data analysis","exploratory data analysis","marketing mix modeling","analysis",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":44},"01M6991VAJ8WFE8KBKNTM6H16F","meridian-doc-consultant","Assists users with questions about Meridian Marketing Mix Modeling and Meridian GeoX geo-experiment concepts, parameters, and best practices by finding and consulting the relevant documentation on developers.google.com\u002Fmeridian. Use when the user asks for explanations or guidance on Meridian MMM or GeoX topics. Don't use for writing code or running models directly.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_doc_consultant\u002FSKILL.md",[],[24,136,137,138,9,139,127,140,29,30,141,32,120,142,122,143,144,37,145,146,147],"consultant","meridian doc consultant","doc","writing","relevant","topics","with","geo","models","best practices","code","documentation",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":44},"01M6991SZPBFVMX04EDK0YH5RV","meridian-budget-optimization","Loads a fitted Meridian model and runs budget optimization scenarios. Use when the user wants to load a saved model and find the optimal budget allocation or target ROI spending. Don't use for visualizing model performance (use meridian-result-visualization) or building\u002Ffitting the model (use meridian-model-building).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmeridian\u002Fblob\u002Fmain\u002Fskills\u002Fmeridian_budget_optimization\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000040","财务",[158,159,160,42,24,161,30,26,32,162,33,34,163,35,37,164,40,25,165,43],"meridian budget optimization","budget optimization","Budget","spending","allocation","budget allocation","find","roi"]