Index of every page on this site: llms.txt
All skills
google avatar

/meridianresultvisualization

@71777a2
by googlegoogle/meridian1.6k stars
314
Run it yourself

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/fitting the model (use meridian-model-building).

  • 4 files
  • 6.6 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/google/meridian/meridianresultvisualization

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈91 tokens for metadata: the name and description. ≈1.3k when used: this file. ≈334 more on demand in 3 files.

Description uses 4.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈365 characters, or 4.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Meridian Result Visualization

A skill for loading a fitted Meridian model and generating standard visualization reports.

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, report paths, script path, 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 output paths for:
    • Model Results Summary report (results_summary.html by default).
  • Prompt the user for the desired path for the generated Python script.
  • Prompt the user for any optional configuration for the reports (e.g., date ranges for results summary).
  • CRITICAL INTERACTIVE CHECKPOINT: Present the gathered paths and configurations to the user and obtain confirmation before loading the model.

2. Add Model Loading Code

  • Use meridian_serde.load_meridian() to load the model.
  • See load_model.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 specify health checks.

3. Add Post-Modeling Health Checks Code (Optional)

  • Use reviewer.ModelReviewer to run health checks and save to HTML.
  • Small / Test Models: If a model has fewer than 2 MCMC draws (e.g. test or mock models where R-hat computation requires >= 2 samples), catch ValueError or skip R-hat calculation gracefully so health check reports generate cleanly.
  • See health_check.md for code template.
  • CRITICAL INTERACTIVE CHECKPOINT: Present the proposed health check report path and code snippet to the user, and obtain approval before continuing to results summary configuration.

4. Add Model Results Summary Code

  • Use summarizer.Summarizer to generate the HTML results summary, applying any user-specified configuration (e.g., date ranges).
    • Date Range Auto-Clipping: If applying a user-specified date range falls outside the model's time coordinates, clip or adjust the date range to match the model's actual coordinates.
    • Tip for errors: If you encounter errors regarding sample_prior, bypass or fix the requirement (for example, by setting sample_prior=False or passing the required parameters) to ensure successful generation.
  • See results_summary.md for code template.
  • CRITICAL INTERACTIVE CHECKPOINT: Present the proposed date ranges, output path configuration, and code snippet for the results summary to the user, and obtain approval before proceeding to script generation and execution.

5. Pre-execution Checkpoint

  • CRITICAL INTERACTIVE CHECKPOINT: Present the final report path and script path to the user, and ask for final confirmation to execute the results generation script now.

6. Execution & Script Setup

  • Write the accumulated Python script to the user-specified path. If your file-writing tool can ask the user to review the written file, don't request that review: the pre-execution checkpoint already asks for approval, and an extra prompt pauses the workflow.
  • Execute the script with the Python interpreter of the environment where google-meridian is installed: the one the user named; else python3 if a virtual environment is already active (VIRTUAL_ENV or CONDA_PREFIX is set); else the project directory's virtual environment (.venv/ or venv/, e.g., .venv/bin/python3) if there is one; else python3. If import meridian fails, ask the user which environment to use instead of searching the machine or installing packages unprompted.
  • CRITICAL: Do NOT delete the generated reports, the script, or the output directory at the end of the task. These are the deliverables requested by the user and must be preserved.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 71777a2. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month

README badge

README badge for google/meridian/meridianresultvisualization