Ocr validate
Skill produtoramaxvision/maxvision-utilities/media-forge/skills/ocr-validate
MaxVision's curated Claude Code marketplace — production-grade skills for n8n workflows, Google Tag Manager API, and more.
npx -y skills add produtoramaxvision/maxvision-utilities --skill ocr-validateAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
INTERNAL - OCR text validation via Cloud Vision. Used by quality-reviewer.
SKILL.md
1.2 KB, 234 tokens by cl100k_base, as published. Nobody here has run it
media-forge:ocr-validate
INTERNAL skill. Validates rendered text accuracy in a generated image using Google Cloud Vision OCR. Called exclusively by media-forge:quality-reviewer.
Workflow
- Receive image path and
expected_textfrom caller context. - Call Cloud Vision API
annotateImagewithTEXT_DETECTIONfeature on the image. - Extract all detected text blocks from the response.
- Compare detected text against
expected_textusing normalized string comparison (trim, lowercase, collapse whitespace). - Return structured result:
{ "pass": boolean, "detected_text": string, "expected_text": string, "mismatch_details": [] }.
When to use
Called internally by quality-reviewer in Stage 1 of the 3-stage review pipeline. Not for direct user invocation.
Outputs
pass: boolean — true if all expected text was detected accuratelydetected_text: full text extracted by OCRmismatch_details: list of{ expected, detected, position }for each discrepancy- Error class on failure:
OCR_MISMATCH