How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/jimmylv/bibigpt-skill --skill bibi-visionBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
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.
