When the user shares an image containing a VIN (photo of dashboard, door jamb, windshield, etc.):
- Make an HTTP POST request to the CarsXE VIN OCR API:
- URL:
https://api.carsxe.com/v1/vinocr?key={CARSXE_API_KEY}&source=codex_plugin - Headers:
Content-Type: application/json - Body:
{ "image": "{IMAGE_URL}" }
- URL:
- Display the extracted VIN and confidence score.
- Offer to immediately decode the VIN using the vehicle-specs skill.
- If the image quality is poor or the VIN can't be extracted, suggest the user try a clearer photo with better lighting and angle.
- If the API key is missing, tell the user to set the
CARSXE_API_KEYenvironment variable (see AGENTS.md).
Source: hashgraph-online/awesome-codex-plugins → plugins/carsxe/carsxe-codex-plugin/skills/vin-ocr/SKILL.md