使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/jimmylv/bibigpt-skill --skill bibi-vision开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
BibiGPT Vision — frames, OCR, mind map
This skill is the visual half of BibiGPT. Same CLI (`bibi`), same account as bibi / bibi-library / bibi-feed. It does not replace a transcript.
Landing: https://bibigpt.co/mcp · Install: https://bibigpt.co/agent · Quota: see references/auth.md
When to use / when not
| Use this skill | Use a sibling instead |
|---|---|
| What's on screen / slides / OCR / PPT | Audio summary or transcript → bibi |
| Generate a mind map (XMind) from a saved item | Saved-library search → bibi-library |
Visual analysis task (extract_video_visuals) | Channel feed → bibi-feed |
Do not offer digital humans, talking-head, lip-sync, or shader generation.
bibi video visuals is Pro-only and rate-limited. If the API returns 403, send the user to https://bibigpt.co/shop
1. Detect mode
Run scripts/bibi-check.sh if present. Prefer CLI (command -v bibi), else $BIBI_API_TOKEN, else MCP https://bibigpt.co/api/mcp. Details: references/auth.md.
2. Intent routing
| User intent | Workflow |
|---|---|
| Frames, slides, on-screen text, OCR | → workflows/visual-analysis.md |
| Mind map / XMind from a saved summary | → workflows/mindmap.md |
Need chapters or a transcript first? Call the bibi skill, then come back.
3. Minimum commands (CLI)
bibi video visuals --videoUrl "https://..." --json
bibi video mindmap --contentId <id> --summary "..." --jsonFull flags: references/cli.md. MCP names: extract_video_visuals, generate_video_mindmap.
