agentleFS
Sign inStart free
gascon-aigascon-ai/claude-skills/loom-transcript/SKILL.md

loom-transcript

Skill0 starsChanged 3 months agoMITView on GitHub

Pull a clean text transcript from any Loom video via Loom's GraphQL API. No download, no Whisper, instant. Use whenever given a loom.com/share link or asked to transcribe, pull, read, or summarize a Loom. Accepts a full Loom URL or a bare 32-char video id.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ccomkhj/skills★ 10same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    No auth for shared or public Looms.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Loom Transcript

Loom has no MCP server. It doesn't need one. Every Loom already has a machine-readable transcript sitting behind its GraphQL API, and this pulls it in one round trip.

Usage

bash ~/.claude/skills/loom-transcript/scripts/loom-transcript.sh "<loom-url-or-id>"

Accepts either form:

bash scripts/loom-transcript.sh "https://www.loom.com/share/24caacbe4181436cab5771dd2802ef05"
bash scripts/loom-transcript.sh 24caacbe4181436cab5771dd2802ef05

Prints the transcript to stdout. Pipe or capture it.

How it works

  1. POST to https://www.loom.com/graphql with FetchVideoTranscript(videoId). It returns VideoTranscriptDetails.source_url, a signed CDN link.
  2. GET that URL. You get JSON with a phrases array, each phrase carrying a readable value.
  3. Join the values.

No auth for shared or public Looms. The signed URL expires, so fetch fresh every time rather than caching it (the script does).

Why not just transcribe it

Because the transcript already exists. Downloading the video and running Whisper on it costs several minutes and a model call to reproduce a file Loom generated at upload time and will hand you for free. Reach for Whisper only when the Loom genuinely has no transcript.

Notes

  • Captions disabled or not yet processed returns a GenericError. The script prints it to stderr and exits non-zero.
  • Docs that embed Looms (shared drives, SOP pages) often carry an inline transcript already. Check there first and skip the call entirely.
  • The 32-char hex id is extracted with a regex, so extra query params on the URL are harmless.

Anti-patterns

  • Caching the source_url. It is signed and short-lived. Re-request it.
  • Running this on a private Loom you aren't authenticated against and reading the error as a bug. It isn't.
  • Feeding the raw transcript straight into a summary without checking length. Long Looms produce long text, so budget context accordingly.

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.

Check your setup, free