PaddleOCR

面向法律 PDF 与扫描件的 PaddleOCR 结构化解析技能。默认将本地 PDF 或图片转换为 Markdown，并在技能内部保留可追溯 archive 归档。本技能应在用户需要法律 PDF OCR、卷宗 OCR、病历 OCR、证据扫描件转 Markdown、表格识别、公式识别、版面分析、PDF 转 Mark...

This skill appears to do what it says: it converts PDFs/images to Markdown and keeps a local archive, calling a PaddleOCR layout-parsing API that you must configure. Before using it with sensitive documents: 1) Fix the registry/config mismatch — SKILL.md and lib.py require PADDLEOCR_DOC_PARSING_API_URL and PADDLEOCR_ACCESS_TOKEN (create paddle-ocr/config/.env as described). 2) Verify the API URL points to a service you trust (self-hosted or a trusted provider). The tool will upload full documents (Base64) to that endpoint with the token in an Authorization header. 3) Run smoke_test.py first (try --skip-api-test to check config, then with a non-sensitive sample to confirm endpoint behavior). 4) If privacy is critical, prefer a local/self-hosted PaddleOCR layout-parsing endpoint (or localhost) so data does not leave your environment. 5) Be aware 'uv' will install Python dependencies at runtime (via PyPI); inspect dependencies if your environment has strict policies. Finally, review the repo/homepage and .env.example to confirm the configured endpoint and token handling meet your security/compliance needs.

Type: OpenClaw Skill Name: paddle-ocr Version: 1.1.1 The paddle-ocr skill bundle is a well-structured tool designed to convert legal PDFs and images into Markdown using the PaddleOCR API. It includes robust features such as automatic PDF batching (scripts/split_pdf.py), image optimization (scripts/optimize_file.py), and a local archival system for traceability. The code uses standard libraries (httpx, pypdfium2, Pillow) and implements proper shell argument quoting in its JXA wrapper (scripts/convert.js) to prevent injection. Network activity is strictly limited to the user-configured API endpoint and a legitimate Baidu-hosted test image (smoke_test.py), with no evidence of data exfiltration or malicious intent.