对 output/captures/ 中的截图运行 OCR，提取文字内容。
执行以下命令：
source .venv/bin/activate && python pipeline.py ocr --input-dir output/captures --output output/extracted_text.txt
完成后读取 output/extracted_text.txt ，将内容展示给用户。
ocr
对 output/captures/ 中的截图运行 OCR，提取文字内容。
Safety Notice
This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.
Copy this and send it to your AI assistant to learn
Install skill "ocr" with this command: npx skills add byzhangkui/video-processing-hub/byzhangkui-video-processing-hub-ocr
Source Transparency
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related Skills
Related by shared tags or category signals.
capture
No summary provided by upstream source.
Repository SourceNeeds Review
process-video
No summary provided by upstream source.
Repository SourceNeeds Review
Invoice Scan
AI-powered invoice scanning and data extraction from images and PDFs. Use when: (1) user sends an invoice image/PDF to scan or extract data from, (2) convert...
Registry SourceRecently Updated
079
Profile unavailable