agentleFS
stardustaistardustai/stardust-skills/skills/video-transcribe/SKILL.md

video-transcribe

Skill0 starsChanged 2 months agoMITView on GitHub

Use when the user asks to transcribe, extract subtitles, summarize a raw transcript, translate, or get text from a YouTube or Bilibili video URL through Stardust Video Transcribe.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Stardust Video Transcribe to extract transcript text from YouTube and Bilibili video URLs.

    line 12
  2. Distinctive:

    Check or remove the Video Transcribe session without starting a job:

    line 34
  3. Distinctive:

    Prefer server-side ASR instead of platform subtitles, or choose language patterns explicitly:

    line 73

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Video Transcribe

Use Stardust Video Transcribe to extract transcript text from YouTube and Bilibili video URLs.

Endpoint

https://video-transcribe.preseen.ai/transcribe

OpenAPI:

https://video-transcribe.preseen.ai/openapi.json

Authentication

The bundled client authenticates through the shared Stardust Cloudflare Access client. The first normal request opens a browser for company login; sign in with an authorized @stardust.ai identity. Refresh tokens stay in the local owner-only store and are isolated by service origin.

Check or remove the Video Transcribe session without starting a job:

python3 "$HOME/.agents/skills/video-transcribe/scripts/video_transcribe.py" --auth-status
python3 "$HOME/.agents/skills/video-transcribe/scripts/video_transcribe.py" --logout

Approved headless workloads set both CF_ACCESS_CLIENT_ID and CF_ACCESS_CLIENT_SECRET from their secret manager. Never set only one or expose either value in chat, source, logs, or reports.

Request

{
  "url": "https://www.youtube.com/watch?v=VIDEO_ID",
  "prefer_subtitles": true,
  "langs": ["zh.*", "en.*"],
  "combine_subtitles": false,
  "keep_workdir": false
}

Usage

python3 "$HOME/.agents/skills/video-transcribe/scripts/video_transcribe.py" \
  "https://www.youtube.com/watch?v=VIDEO_ID"

Return the complete response as JSON and save it:

python3 "$HOME/.agents/skills/video-transcribe/scripts/video_transcribe.py" \
  "https://www.bilibili.com/video/BV..." \
  --format json \
  --output "/absolute/path/to/transcript.json"

Prefer server-side ASR instead of platform subtitles, or choose language patterns explicitly:

python3 "$HOME/.agents/skills/video-transcribe/scripts/video_transcribe.py" \
  "https://www.youtube.com/watch?v=VIDEO_ID" \
  --no-prefer-subtitles \
  --lang 'zh.*' \
  --lang 'en.*'

Return the text field to the user or use it as source material for summarization, translation, or analysis. Preserve source, title, and video_id in citations when useful.

Notes

  • source=subtitles means the service used platform captions.
  • source=funasr means the service downloaded audio and ran server-side ASR.
  • For private Bilibili or member videos, configure server-side cookies. Do not send browser cookies in chat.
  • The hostname needs its own Cloudflare Access application and AUD. If metadata is missing, rule out a local 198.18.x.x fake-IP/proxy path before treating it as a service-side configuration problem.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.