Scribe

anthropics/knowledge-work-pluginsOfficial

Route here when you need to transcribe uploaded audio or video files using Zoom's AI Services Scribe API. It covers both fast mode for single files under 100MB and batch jobs for larger archives, plus Build-platform JWT auth and webhook-driven pipelines. The routing guardrail is clear: use this for stored media, not live meetings. There's a useful pseudo-streaming pattern for browser microphone capture via repeated short uploads, though it's explicitly a fallback demo pattern with chunk-boundary drift and stitching complexity. The hosted fast-mode guardrail is honest about frontend 504 timeouts on larger files even when the backend succeeds, which saves you debugging time.

skills.sh installs: 2.2K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill scribe --agent claude-code

Installs into .claude/skills of the current project.

Files

Zoom AI Services Scribe

Background reference for Zoom AI Services Scribe across:

synchronous single-file transcription (POST /aiservices/scribe/transcribe)
asynchronous batch jobs (/aiservices/scribe/jobs*)
browser microphone pseudo-streaming via repeated short file uploads
webhook-driven batch status updates
Build-platform JWT generation and credential handling

Official docs:

Routing Guardrail

If the user needs uploaded or stored media transcribed into text, route here first.
If the user needs live meeting media without file-based upload/batch jobs, route to ../rtms/SKILL.md.
If the user needs Zoom REST API inventory for AI Services paths, chain ../rest-api/SKILL.md.
If the user needs webhook signature patterns or generic HMAC receiver hardening, optionally chain ../webhooks/SKILL.md.

SKILL.md on GitHub

Details

Repository: github.com/anthropics/knowledge-work-plugins
Categories: Backend & APIs, DevOps & CI/CD, Automation & Workflows, Sales & Marketing, Design & UI/UX
First seen: Jun 3, 2026