New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Meridian Scenario Planner

by google in google/meridian

Generates Scenario Planner data from a fitted Meridian marketing mix model and prepares it for a Looker Studio dashboard through a Colab handoff.

OfficialApache-2.0Auto-check passedData & Analytics

Install Meridian Scenario Planner

skills CLI
$ npx skills add google/meridian --skill meridian-scenario-planner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install google/meridian meridian-scenario-planner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/google/meridian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/meridian_scenario_planner .claude/skills/meridian-scenario-planner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
meridian-scenario-planner
GitHub stars
1.6k
Token cost
~1.5k tokens
SKILL.md length
623 words
Files
2 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generates Scenario Planner data from a fitted Meridian marketing mix model and prepares it for a Looker Studio dashboard through a Colab handoff.

  • Works in 6 steps: Initial Setup → Configure Scenario Planner Spec &… → Add Model Loading Code → …
  • Producing scenario planning data and budget grids from a saved Meridian model
  • SKILL.md covers Prerequisites and Core Workflow
  • Reaches colab.research.google.com

What it does

The skill works from a fitted Meridian model saved as meridian_model.binpb. That file is binary, so the agent loads it with meridian_serde.load_meridian() in a Python script instead of reading it as text. It asks for the model path, the output proto path (model_build/scenario_planner_data.binpb by default) and where to save the generated script (model_build/run_scenario_planner.py by default).

At each checkpoint it presents the proposed paths and Scenario Planner spec settings and waits for your confirmation, even if you asked it to run autonomously. The result is a proto file for a Colab handoff, which needs no Google Cloud setup, plus a link to the Meridian Looker Studio Scenario Planner notebook. It is not for visualizing model results or running standard budget optimization, which other Meridian skills cover.

When your agent uses it

  • Producing scenario planning data and budget grids from a saved Meridian model
  • Preparing a Looker Studio scenario dashboard from marketing mix model output

Example prompts

  • “Generate Scenario Planner data from ./model/meridian_model.binpb for Looker Studio.”
  • “Build the budget grids from my saved Meridian model and give me the Colab link.”

Requirements

  • A fitted Meridian model saved as meridian_model.binpb
  • A Python environment where meridian_serde can be imported

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Initial Setup
  2. Configure Scenario Planner Spec & Interactive Checkpoint
  3. Add Model Loading Code
  4. Add Scenario Planner Data Generation & Colab Handoff Code
  5. Pre-execution Checkpoint
  6. Execution & Script Setup

What it can do on your machine

Read from SKILL.md and the folder at commit c800637. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • colab.research.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Meridian Scenario Planner loads about 1.5k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 623 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from google/meridian at commit c800637, republished under its Apache-2.0 licence (© google). 623 words, ~1,470 tokens.

Download SKILL.mdSave it as .claude/skills/meridian-scenario-planner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
meridian-scenario-planner
description
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).

Meridian Scenario Planner Generation

This skill guides the agent to generate Scenario Planner data, serialize it as a proto file for Colab handoff (zero GCP setup required), and provide the link to the Meridian Looker Studio Scenario Planner Colab notebook.

Prerequisites

  • The agent must have access to a fitted Meridian model (serialized as meridian_model.binpb).

  • [!IMPORTANT] meridian_model.binpb is a binary file. Do NOT try to read its content directly using file viewing tools or grep, as this will produce invalid UTF-8 errors. Always use meridian_serde.load_meridian() in a Python script to load it.

Core Workflow

Interactivity Checkpoint Rule

Throughout this workflow, you will encounter CRITICAL INTERACTIVE CHECKPOINTs. At each checkpoint, you MUST:

  1. Present the current proposed configurations, paths, or status to the user for approval.
  2. Ask the user if they are ready to proceed using the available user-interaction tool (e.g., ask_question), structured as a multiple-choice question. Do NOT use raw chat text.
  3. Wait for their response before proceeding.
    • MANDATORY: You MUST pause at every checkpoint regardless of the initial prompt instructions (even if the user request contains phrases like "run autonomously", "execute directly", "fix autonomously", etc.). The initial request does NOT bypass these interactive checkpoints.
    • Note: If the user replies to a checkpoint with a generic approval (e.g., "proceed", "do what you think is best"), proceed with the proposed defaults.
1. Initial Setup
  • Prompt the user for the path to the serialized model file (meridian_model.binpb by default).
  • Prompt the user for the output proto path (default: model_build/scenario_planner_data.binpb).
  • Prompt the user for the desired path for the generated Python script. If unspecified, default to model_build/run_scenario_planner.py (or relative to the model directory).
  • CRITICAL INTERACTIVE CHECKPOINT: Present the gathered paths to the user and obtain confirmation before configuring spec parameters.
2. Configure Scenario Planner Spec & Interactive Checkpoint
  • Prompt the user for the following Scenario Planner spec configurations (or confirm defaults):
    • optimization_name (String, e.g., "Scenario Planner")
    • include_non_paid_channels (Boolean, default: True)
    • Time breakdown: yearly (default: False), quarterly (default: True), monthly (default: False)
    • min_spend_shift_ratio (Float 0-1, default: 1.0)
    • max_spend_shift_ratio (Float > 0, default: 1.0)
    • use_optimal_frequency (Boolean, default: True)
    • max_frequency (Float > 0, default: 10.0)
  • CRITICAL INTERACTIVE CHECKPOINT: Present the proposed Scenario Planner spec configurations to the user and obtain approval before continuing to load the model.
Show full SKILL.md (254 more words)Show less
3. Add Model Loading Code
  • Use meridian_serde.load_meridian() to load the model.
  • See script_template.md for code template.
  • CRITICAL INTERACTIVE CHECKPOINT: Present the model load path configuration and proposed Python code snippet to the user, and obtain approval before continuing to data generation.
4. Add Scenario Planner Data Generation & Colab Handoff Code
  • Create specs for ModelFitSpec, MarketingAnalysisSpec, and BudgetOptimizationSpec using the user-provided configurations.
  • Use mmm_ui_gen.create_mmm_ui_data_proto() to create the proto, including the requested time breakdown generators.
  • Serialize and save the proto to disk (e.g. model_build/scenario_planner_data.binpb).
  • Instruct the user to upload the saved file to the Meridian Scenario Planner Colab notebook: https://colab.research.google.com/github/google/meridian/blob/main/demo/Meridian_Scenario_Planner_Beta.ipynb
  • See script_template.md for code template.
  • CRITICAL INTERACTIVE CHECKPOINT: Present the proposed scenario planner spec configuration and export code snippet to the user, and obtain approval before continuing to execution.
5. Pre-execution Checkpoint
  • CRITICAL INTERACTIVE CHECKPOINT: Ask the user for final confirmation to execute the scenario planner generation script now.
6. Execution & Script Setup
  • Write the accumulated Python script to the user-specified path. When writing the file using write_to_file, explicitly set ArtifactMetadata.RequestFeedback=false to avoid pausing execution.
  • You can use the full script template in script_template.md as a guide.
  • Execute the script using Python: prefer the active virtual environment if available (e.g. .venv/bin/python3 or /tmp/meridian_eval_cache/bin/python3, otherwise python3).
  • When executing the script, if run_command runs as a background task, simply end the turn and wait for the completion notification.
  • CRITICAL: Do NOT delete the generated script, output proto files, or deliverables at the end of the task. These are the deliverables requested by the user and must be preserved.

© google, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/meridian_scenario_planner of google/meridian.

  • SKILL.md
  • references/script_template.md

Open the folder on GitHubat commit c800637

Compare with similar skills

Meridian Scenario Planner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Meridian Scenario Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meridian Scenario Planner this skillgoogle/meridian1.6k—~1.5kAutomated safety check: PassApache-2.0
Save Research Notebooknapjon/krisk117—~702Automated safety check: PassBSD-3-Clause
Analytics Data AnalysisMindrally/skills271—~1.6kAutomated safety check: PassApache-2.0
Export ML Notebookprobabl-ai/skills138—~1.7kAutomated safety check: PassBSD-3-Clause
Excel and CSV Data Analysisbytedance/deer-flow84k4 repos~2.2kAutomated safety check: PassMIT
Pandas ProJeffallan/claude-skills12k1 repos~1.5kAutomated safety check: PassMIT

Similar skills

  • Save Research Notebook

    napjon/krisk

    Convert a completed data-analysis conversation into evidence-backed, reproducible living research through the Krisk MCP server.

    117 GitHub stars~702 tokensUpdated 9 days ago
    Data & AnalyticsAuto-check passed

  • Analytics Data Analysis

    Mindrally/skills

    Best practices for analytics, data analysis, and visualization using Python, pandas, matplotlib, seaborn, and Jupyter notebooks.

    271 GitHub stars~1.6k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed

  • Export ML Notebook

    probabl-ai/skills

    Write a jupytext percent %% Python file out as an .ipynb. An agent skill from probabl-ai/skills.

    138 GitHub stars~1.7k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Excel and CSV Data Analysis

    bytedance/deer-flow

    Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.

    84k GitHub starsUsed in 4 repos~2.2k tokens
    Data & AnalyticsAuto-check passed

  • Pandas Pro

    Jeffallan/claude-skills

    Handles pandas DataFrame work: cleaning, merging, groupby aggregation, pivots, time-series resampling and memory tuning, with checks on dtypes, shapes and nulls.

    12k GitHub starsUsed in 1 repo~1.5k tokens
    Data & AnalyticsAuto-check passed

  • Python Executor

    cortega26/chile-hub

    Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).

    113 GitHub starsUsed in 2 repos~1.5k tokens
    Data & AnalyticsAuto-check passed

More from google/meridian

  • Meridian Budget Optimization

    google/meridian

    Official

    Reopens a fitted Meridian MMM from a saved file and runs budget allocation scenarios, producing an HTML report and a Python script that repeats the run.

    1.6k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Meridian MMM Documentation Consultant

    google/meridian

    Official

    Finds and reads the right Meridian marketing-mix-modeling documentation file to answer a concept or parameter question, instead of guessing.

    1.6k GitHub stars~896 tokensUpdated yesterday
    Auto-check passed

  • Meridian MMM Model Building

    google/meridian

    Official

    Takes a user through building a Meridian marketing mix model, from loading CSV data and mapping columns to running EDA, fitting and saving the model.

    1.6k GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Meridian Result Visualization

    google/meridian

    Official

    Loads a saved Meridian MMM model and produces an HTML results summary, with optional health checks and approval checkpoints at each step.

    1.6k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Meridian Scenario Planner

What does Meridian Scenario Planner do?

Generates Scenario Planner data from a fitted Meridian marketing mix model and prepares it for a Looker Studio dashboard through a Colab handoff. binpb.load_meridian() in a Python script instead of reading it as text.

When should I use Meridian Scenario Planner?

Meridian Scenario Planner fits situations like: producing scenario planning data and budget grids from a saved Meridian model; preparing a Looker Studio scenario dashboard from marketing mix model output.

How do I install Meridian Scenario Planner in Claude Code?

Run `npx skills add google/meridian --skill meridian-scenario-planner -a claude-code`. Or copy the skill folder (skills/meridian_scenario_planner in google/meridian) into .claude/skills/meridian-scenario-planner in your project. Claude Code loads it when a task matches its description.

How do I install Meridian Scenario Planner in Codex?

Run `npx skills add google/meridian --skill meridian-scenario-planner -a codex`. Or copy the skill folder (skills/meridian_scenario_planner in google/meridian) into .agents/skills/meridian-scenario-planner in your project. Codex loads it when a task matches its description.

Can I use Meridian Scenario Planner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google/meridian --skill meridian-scenario-planner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meridian-scenario-planner, .gemini/skills/meridian-scenario-planner, .github/skills/meridian-scenario-planner and .opencode/skills/meridian-scenario-planner in your project.

What does Meridian Scenario Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Meridian Scenario Planner is instructions for the agent only. Our summary lists: A fitted Meridian model saved as meridian_model.binpb; A Python environment where meridian_serde can be imported.

Does Meridian Scenario Planner access the network?

SKILL.md names 1 domain. In commands or code: colab.research.google.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Meridian Scenario Planner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Meridian Scenario Planner use?

Meridian Scenario Planner is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meridian Scenario Planner use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.

What are the alternatives to Meridian Scenario Planner?

Skills that share tags, products or a category with Meridian Scenario Planner: Save Research Notebook (napjon/krisk, 117 stars), Analytics Data Analysis (Mindrally/skills, 271 stars), Export ML Notebook (probabl-ai/skills, 138 stars) and Excel and CSV Data Analysis (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meridian Scenario Planner?

google (a GitHub organization, an official publisher) maintains it in google/meridian, which has 1,562 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 9, 2026.

Source: google/meridian on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.