OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add aotenjou/silicon-paddleocr --skill silicon-paddle-ocr
OCR skill using PaddleOCR model via SiliconFlow API. This skill should be used when the user asks to "recognize text from an image", "extract text from a photo", "OCR this image", "read text from screenshot", or mentions "PaddleOCR", "image text recognition", "text extraction from images".
npx skills add aotenjou/silicon-paddleocr --skill silicon-paddle-ocr
Use PaddleOCR to extract text content from images. Supports single image or batch processing.
This skill provides optical character recognition (OCR) capabilities using the PaddlePaddle/PaddleOCR-VL-1.5 model via the SiliconFlow API. Extract text from JPG, PNG, WebP, BMP, and GIF images.
Invoke this skill when:
Ensure the SILICONFLOW_API_KEY environment variable is set:
Execute the OCR script:
| Argument | Description |
|---|---|
images | Image file path(s) or glob pattern (required) |
-k, --api-key | API key (default: from SILICONFLOW_API_KEY env) |
-m, --model | OCR model name (default: PaddlePaddle/PaddleOCR-VL-1.5) |
-p, --prompt | Recognition prompt for custom behavior |
-j, --json | Output results in JSON format |
-o, --output | Save results to specified file |
--max-tokens | Maximum tokens in response (default: 2000) |
Single image:
Multiple images with glob:
JSON output format:
Custom prompt for table extraction:
Save to file:
Text output (default):
JSON output:
Coordinates Explanation:
box field provides the four corner coordinates of each text region in pixel formatIf processing fails:
Images that fail to process will show an error message, and other images will continue processing.
references/api-configuration.md - API configuration detailsexamples/sample-usage.sh - Example usage scriptscripts/ocr_skill.py - The main OCR implementationpython3 scripts/ocr_skill.py --json /path/to/image.jpgpython3 scripts/ocr_skill.py -p "Please identify and format table content as Markdown" /path/to/table.jpgpython3 scripts/ocr_skill.py --json --output results.json /path/to/images/*.jpg--- image.jpg ---
识别到的文字内容
识别到 X 处文字区域{
"image.jpg": {
"image_path": "/path/to/image.jpg",
"image_size": [width, height],
"texts": [
{
"text": "识别的文字",
"box": [[x1, y1], [x2, y2], [x3, y3], [x4, y4]]
}
],
"full_text": "所有文本的组合"
},
"image2.png": { ... }
}