In brief
Serves when using Scribe, the transcription service of the Zoom IA services. The skill applies to Scribe transcription pipelines, on a remote or stored media. If the user needs the media for a live meeting, you should first compare with RTMS or an SDK bot meeting stream. It asks to confirm the source, size, language, expected latency, and if a rapide mode or batch mode is appropriate, to set up the building platform identifiers and JWT management apart from the transcription logic, then design ingestion, cutting, new attempts, webhook reminders and persistence, before linking downstream AI streams.
What it does
- Transmits an uploaded or stored media in rapide or batch mode
- Returns media from a live meeting to GRTS or a bot Meeting SDK
Who it is for, and an example
Teams that transcribe a media already filed or stored, rather than the live stream of a meeting.
Example request: "Transcrire this file with Scribe, in batch mode, with webhook reminders; for a live meeting, compares instead gtrS. »
It is used for a Scribe transcript on an uploaded or stored media, and it asks to compare with RTMS or an SDK bot meeting for the media of a live meeting. Example written by iadujour.fr from the SKILL.md, not tested.
Install
In Codex: codex plugin add zoom@openai-curated (Official Place of Deposit).
codex plugin add zoom@openai-curatedWorks with
- Codex
Source: README: Codex plugin collection; the deposit marketplace is called "Official Codex". Other officers are not appointed.
Level: Intermediate
Suppose a project already in place at the publisher and the tools described in SKILL.md.
Good to know
SKILL.md excerpt
The original description, which the agent reads to decide whether to load the skill (in English):
Use when using Scribe.
Quoted from SKILL.md at commit ed8ce2e . The folder also contains 12 extra files (agents/, concepts/, examples/, references/, scenarios/, troubleshooting/).
The SKILL.md has 21 lines and 2 main sections:
- Workflow
- References
Licence: MIT
Checked on 10 November 2026 : parent-folder licence file (plugins/zoom/LICENSE) . Rights holder: Copyright (c) 2025 Zoom Video Communications, Inc..
The licence allows reuse: the full SKILL.md text is reproduced below, unmodified, with its licence notice.
Full SKILL.md text
Reproduced unmodified from openai/plugins (commit ed8ce2e) , © OpenAI, under licence MIT (original licence file ).
Show the original SKILL.md (21 lines, in English)
---
name: scribe
description: Use when using Scribe.
---
# Zoom AI Services Scribe
Use this skill for Zoom Scribe transcription pipelines over uploaded or stored media. If the user needs live meeting media, compare against RTMS or Meeting SDK bot workflows first.
## Workflow
1. Confirm the media source, size, language, expected latency, and whether fast mode or batch mode fits.
2. Set up Build-platform credentials and JWT handling separately from application transcription logic.
3. Design ingestion, chunking, retries, webhook callbacks, and persistence before connecting downstream AI workflows.
4. Implement a minimal transcription request and response parser, then add batching and operational monitoring.
5. Debug by checking credential audience, processing mode, media format, file size, backend timeout, and webhook delivery.
## References
- Full preserved guide: [references/full-guide.md](references/full-guide.md)
- Auth and processing modes: [concepts/auth-and-processing-modes.md](concepts/auth-and-processing-modes.md)
- High-level scenarios: [scenarios/high-level-scenarios.md](scenarios/high-level-scenarios.md)
- Fast mode Node example: [examples/fast-mode-node.md](examples/fast-mode-node.md)
- Batch webhook pipeline: [examples/batch-webhook-pipeline.md](examples/batch-webhook-pipeline.md)
- API reference: [references/api-reference.md](references/api-reference.md)
- Common drift and breaks: [troubleshooting/common-drift-and-breaks.md](troubleshooting/common-drift-and-breaks.md)
Comments.
A field note, a question, a precision on this skill? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.