--- name: chompute-lpr description: >- Detect and read license plates using Chompute's API, returning structured JSON with bounding boxes, OCR text, confidence, and per-character confidence values. Use when the user asks to detect license plates, read a plate from an image, run ALPR/LPR on an image, or extract plate text and bounding boxes from a local image file or image URL. --- # Chompute License Plate Recognition Detects license plates in an image and returns structured JSON with detection and OCR results. ## Prerequisites This skill requires a Chompute Access Key. Check for the key in this order: 1. `CHOMPUTE_API_KEY` 2. `CLAUDE_PLUGIN_OPTION_chompute_api_key` 3. `CLAUDE_PLUGIN_OPTION_CHOMPUTE_API_KEY` 4. `chompute_key.txt` in this skill's directory (same folder as this SKILL.md) If none of these exists or the value is empty, tell the user: > You need a Chompute Access Key. Sign up and get one at: > https://chompute.ai/skills > > Then set `CHOMPUTE_API_KEY`, configure the plugin's Chompute Access Key option, > or save your key to: `/chompute_key.txt` Stop and do not continue without a valid key file. If a valid key is present, use it without printing it and tell the user: > Valid Access Key present. Proceeding... ## Workflow 1. **Read the input image** attached or mentioned in the message. Do NOT automatically pick images from the folder. The image must be mentioned or attached by the user. The input may be either: - a local image file path, or - a direct HTTP(S) image URL If there is no image attached, mentioned, or linked, tell the user the following and then stop: > Please attach, mention, or provide an image URL for license plate recognition. 2. **Prepare the API input**: - If the input is a local file, base64-encode the file contents and send a `data:;base64,` value in `image_url`. - If the input is an HTTP(S) image URL, pass that URL directly in `image_url` without base64-encoding it yourself. 3. **Call the Chompute API** using the contract below. Use whatever HTTP method is available in the environment (curl, python, node, etc.). 4. **Parse the response.** On success, read the JSON in `output_text` and extract the LPR results. - `results` is a list of detections - each result can include: - `detection.bbox` - `detection.confidence` - `detection.label` - `ocr.text` - `ocr.confidence` - `ocr.char_confidences` - `lpr_model_config` contains model metadata 5. **Present the result clearly** to the user: - Do NOT say things like "the chompute-lpr skill found..." or otherwise make the summary sound like a tool log - Start with a natural summary in plain English - If one plate is found, say: `I found 1 license plate in the image. The plate reads .` - If multiple plates are found, say how many were detected and list the detected plate texts that have non-empty OCR values - If OCR text is missing for a detection, mention that a plate was detected but the text could not be read confidently - If `results` is empty, say: `I did not detect any license plate in this image.` - After the short summary, add a short non-technical explanation section called `What this means:` - In `What this means:`, include 2-4 short bullets, depending on what is available: - `Plate text: ` - `OCR confidence: %` - `Detection confidence: %` - `Location in image: ` - Round confidence values to a friendly percentage format before showing them to the user - Keep the explanation concise and user-friendly; assume the reader is not technical - Then add a short label: `Technical details (JSON):` - Only after that label, provide the structured JSON result in a code block - Do NOT put the raw JSON immediately after the first sentence with no explanation 6. **On error**, show the error details to the user. If the API returns 401, tell the user their Access Key may be invalid or expired and direct them to https://chompute.ai to check their account. ## API Contract ### Request ``` POST https://chompute-services.dragonfruit.ai/openai/v1/responses Content-Type: application/json Authorization: Bearer ``` Body: ```json { "model": "license-plate-recognition", "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "Use the license plate recognition skill on this image." }, { "type": "input_image", "image_url": "" } ] } ] } ``` Where `` is either: - `data:;base64,` for a local file, or - a direct HTTP(S) image URL ### Response The response JSON contains `output_text`, which is a JSON string representing the LPR result. Example (truncated): ```json { "output_text": "{\n \"lpr_model_config\": {\"detector_size\": 384},\n \"results\": [{\"detection\": {\"bbox\": [787, 383, 863, 440], \"confidence\": 0.30, \"label\": \"license_plate\"}, \"ocr\": {\"text\": \"AXWV973\", \"confidence\": 0.99, \"char_confidences\": [0.99, 0.99]}}]\n}" } ``` Parse `output_text` as JSON before presenting the final result.

chompute-lpr

Install this skill

Comments