Install
openclaw skills install skills-sh:jimmylv/bibigpt-skill/bibiBibiGPT — video summarizer agent skill (summarize / transcript / chapters) This file is a discovery stub, not the usage guide. It tells you which mode you are in and where the live docs are. The live sources always match the current product; anything copied into this file…
openclaw skills install skills-sh:jimmylv/bibigpt-skill/bibiThis file is a discovery stub, not the usage guide. It tells you which mode you are in and where the live docs are. The live sources always match the current product; anything copied into this file would go stale.
This skill is watch-video only. Sibling skills in the same repo (same CLI,
same account): bibi-library (saved videos / notes / collections),
bibi-feed (subscribe / latest / mark seen), bibi-vision (frames / mind map).
Landing: https://bibigpt.co/mcp · Human install: https://bibigpt.co/agent
Quota: Plus 100/day, Pro 300/day on the agent-skill channel; extra calls use
API balance; upgrade https://bibigpt.co/shop
Run scripts/bibi-check.sh if present, or check in order:
| Check | Mode | Notes |
|---|---|---|
command -v bibi | CLI — best: local files, desktop login | macOS / Windows / Linux desktop app |
$BIBI_API_TOKEN set | API — HTTP calls, works anywhere | token: https://bibigpt.co/user/integration |
| MCP client available | MCP — zero install | connect https://bibigpt.co/api/mcp (OAuth 2.1) |
Neither available → install the desktop app (brew install --cask jimmylv/bibigpt/bibigpt
on macOS, winget install BibiGPT on Windows, curl -fsSL https://bibigpt.co/install.sh | bash
on Linux) or get an API token. Details: references/installation.md.
CLI mode — the CLI is the always-current doc source:
bibi check-update # once per session; run `bibi upgrade` if outdated
bibi --help # full command surface, grouped, with examples
bibi <command> --help # progressive help — every --help includes examples
bibi commands # re-fetch server-defined commands (new capabilities
# appear here without a binary update)
API mode — the machine-readable spec is the source of truth:
https://bibigpt.co/api/openapi.json # all endpoints, schemas, auth
references/api.md has curl examples but the spec wins on conflict.
MCP mode — connect and list tools; they are self-describing:
https://bibigpt.co/api/mcp # Streamable HTTP, OAuth 2.1
Latest docs without reinstalling — this repo is served raw from GitHub:
https://raw.githubusercontent.com/JimmyLv/bibigpt-skill/main/skills/bibi/SKILL.md
https://raw.githubusercontent.com/JimmyLv/bibigpt-skill/main/skills/bibi/references/<name>.md
https://raw.githubusercontent.com/JimmyLv/bibigpt-skill/main/skills/bibi/workflows/<name>.md
If a local workflows/ or references/ path below is missing (embedded-only
install via bibi skill), fetch it from the raw URL above instead.
| User Intent | Workflow |
|---|---|
| Summarize a video/audio URL | → workflows/quick-summary.md |
| Chapter-by-chapter breakdown, detailed analysis | → workflows/deep-dive.md |
| Get subtitles, extract transcript, raw text | → workflows/transcript-extract.md |
| Turn into article, blog post, 公众号图文, 小红书 | → workflows/article-rewrite.md |
| Turn into TikTok / Reels / Shorts-style music video | → workflows/video-to-tiktok-mv.md |
| Process multiple URLs, batch summarize | → workflows/batch-process.md |
| Research a topic across multiple videos | → workflows/research-compile.md |
| Save to Notion, Obsidian, export notes | → workflows/export-notes.md |
| Analyze visual content, slides, on-screen text, mind map | → sibling skill bibi-vision (fallback: workflows/visual-analysis.md / workflows/advanced-tools.md) |
| Check current account, plan, or remaining minutes | → workflows/account-check.md |
| Browse / search saved videos, "what have I summarized" | → sibling skill bibi-library (fallback: workflows/library-browse.md) |
| Manage channel subscriptions, list/sub/unsub | → sibling skill bibi-feed (fallback: workflows/channels-manage.md) |
| What's new across my subscriptions, latest feed, daily digest | → sibling skill bibi-feed (fallback: workflows/feed-latest.md) |
| Manage collections, list/create/share saved videos as a set | → sibling skill bibi-library (fallback: workflows/collections-manage.md) |
| Manage personal notes on saved videos, edit summaries | → sibling skill bibi-library (fallback: workflows/notes-manage.md) |
| Custom-prompt re-summary of a saved item, collection chat | → sibling skill bibi-library (fallback: workflows/advanced-tools.md) |
| HTTP 402 / "需要付款" / Alipay AI 钱包 / no token + China user | → references/billing-aipay.md |
Disambiguation: intent matches more than one workflow → ask one clarifying
question first. Matches none → ask what they want; do not guess. Bare URL
with no context → default to workflows/quick-summary.md.
For single-command requests that don't need a full workflow — discover the
rest via bibi --help:
bibi summarize "<URL-or-local-file>" # quick summary (local: .mp4 .mp3 .m4a ...)
bibi summarize "<INPUT>" --chapter # chapter summary
bibi summarize "<INPUT>" --subtitle # transcript only
bibi me # account, plan, remaining minutes
URLs containing ? or & must be quoted. API mode has no local-file upload —
guide the user to a public URL (OSS/S3) first, see references/supported-platforms.md.
If no auth is set and the user has an Alipay account, BibiGPT may respond
with HTTP 402 Payment Required + Payment-Needed header (AI 收 protocol).
The bibi CLI prints a stable marker line [HTTP/402 Payment Required] to
stderr before any human-readable prompt. When either signal appears, route to
references/billing-aipay.md instead of treating the call as failed — the
agent can resolve payment automatically via
@alipay/agent-payment
or a one-off QR purchase.
bbef2e3524b3