To run this task you must have the following required information:

> Health score value (0-100) or use a sample visualization

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).

Add all steps to your todo list now and begin executing.

## Steps

1. [Read Customer Success Visual Prompts]: Read the documentation in: `./skills/sauna/[skill_id]/references/success.visual.prompts.md` (Get the health gauge prompt template)

2. Ask the user for their health gauge details:
- What score should the gauge show? (0-100, or "sample" for a demo at 75)
- Any specific color scheme? (Default: red/orange/yellow/green traffic light)

If user just says "health score gauge" without details, create a sample at score 75.


3. Construct the image generation prompt using the Health Score Gauge template:

1. Start with the base template from the slice
2. Replace [score] with the user's score value
3. Determine which color zone the score falls into:
   - 0-39: red (Critical)
   - 40-59: orange (At Risk)
   - 60-79: yellow (Needs Attention)
   - 80-100: green (Healthy)
4. Customize colors if the user specified a different scheme
5. Keep the dashboard-style, professional aesthetic

The final prompt should be specific for consistent results.


4. [Gather Arguments: Generate or Edit Image] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `prompt`: the constructed prompt from previous step
- `imagePath`: empty string - no source image for generation
- `outputDir`: ./documents/images/**/*

5. [Run Code: Generate or Edit Image]: Call `run_script` with:

```json
{
  "file": {
    "path": https://sk.ills.app/code/media.image.generate/preview,
    "args": [
      "prompt",
      "imagePath",
      "outputDir"
    ]
  },
  "packages": null
}
```

6. Present the generated health gauge to the user. Show the saved image path.
Offer to regenerate with a different score or color scheme if needed.