process-video

source .venv/bin/activate && python pipeline.py process --save-dir output/captures --interval 500

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 "process-video" with this command: npx skills add byzhangkui/video-processing-hub/byzhangkui-video-processing-hub-process-video

完整的视频处理流程,分三步执行:

步骤 1 + 2 - 截图并自动 OCR

source .venv/bin/activate && python pipeline.py process --save-dir output/captures --interval 500

告知用户:

  • 点击 "Select Area" 选择屏幕上的视频区域

  • 点击 "Start Capture" 开始定时截图

  • 播放视频

  • 截图会在停止后自动结束(无新截图超过 interval*2 时自动停止),然后自动运行 OCR

等待命令执行完毕。

步骤 3 - 生成文章

读取 output/extracted_text.txt ,将零散的 OCR 文字整理成一篇通顺的 Markdown 文章:

  • 去除 OCR 噪音(乱码、非视频内容的 UI 文字等)

  • 去除重复和无意义的内容

  • 按逻辑组织段落

  • 语言通顺,保留原意

将最终文章写入 output/article.md 文件,并告知用户文件路径。

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.

General

capture

No summary provided by upstream source.

Repository SourceNeeds Review
General

ocr

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated