generate-json-from-data

---

name: generate-json-from-data description: This prompt instructs the AI to take provided text or an image as input, extract the relevant information, and convert it into a structured JSON representation. The outcome is a JSON output formatted inside a Markdown code block, suitable for easy copying, parsing, or downstream processing. compatibility: Requires betterprompt >= 0.1.0

What it does

This prompt instructs the AI to take provided text or an image as input, extract the relevant information, and convert it into a structured JSON representation. The outcome is a JSON output formatted inside a Markdown code block, suitable for easy copying, parsing, or downstream processing.

For more installation instructions go to https://skills.sh/betterpromptme/betterprompt/betterprompt to check out this skill.

Inputs

textInputs

Pass each text input using --input <key>=<value> flags.

Variable key	Required?	Description	Defaults
DATA	Required		(none)

imageInputs

This prompt requires exactly 1 image. You must pass exactly 1 image flag (no more, no fewer), in the order matching the descriptions below.

Index	Required	Description	Allowed CLI flags
1	Yes	Image to describe	--image-input-url <url> or --image-input-base64 <base64> or --image-input-path <absolute path to image>

Models and options

This skill's modality is: text.

To discover which model values you can use (and which options keys/values are valid for each model), run:

betterprompt resources --models-only --json

Then filter the returned JSON array to entries where modality is "text".

How to run

Step 1: Collect inputs

First, run betterprompt resources --models-only --json and filter to modality: "text" to discover valid models and available options:

betterprompt resources --models-only --json

Use only the models and option values that appear in the filtered results.

Then collect all inputs from the human:

• Required text inputs:
  • DATA
• Required images:
  • Exactly 1 images: image 1 (Image to describe). Images must be provided in this order.
• Optional: model and options.
  • Present the human with the default model gpt-5-mini and its available options. Look up gpt-5-mini in the betterprompt resources output (filtered to modality "text") and show its availableOptions as: key: val1, val2 (default), val3 | key2: .... Mark a value (default) if it matches these defaults: {}.
  • If the human does not specify, defaults are used: model gpt-5-mini, options {}. Other models from the resources call are also available.

If any required text input or the required images are missing, ask the human for what's missing. Do not assume or fabricate values. Tell the human: "Please provide images in this order: image 1 (Image to describe)".

Step 2: Run via BetterPrompt CLI

Use the frontmatter's name as the positional argument (for this skill, use generate-json-from-data).

Command form:

betterprompt generate generate-json-from-data \
  [--input <key>=<value>] \
  [--image-input-url <url>] \
  [--image-input-base64 <base64>] \
  [--image-input-path <absolute path to image>] \
  [--model <model>] \
  [--options <options JSON>] \
  [--json]

Notes:

• Pass each text input as a separate --input <key>=<value> flag.
• Pass each image using one of --image-input-url, --image-input-base64, or --image-input-path, in the order matching the imageInputs descriptions (image 1 first, then image 2, etc.).
• If the human does not mention a model, omit --model and BetterPrompt will use the default model: gpt-5-mini.
• If the human does not mention options, omit --options and BetterPrompt will use the default options: {}.
• If the run times out, the response will include a runId you can use to fetch the result later.

Example (using defaults shown above):

betterprompt generate generate-json-from-data \
  --input DATA=<value> \
  --image-input-url https://example.com/image1.png \
  --model gpt-5-mini \
  --options '{}'