Agent Skills
› openai/plugins
› scribe
scribe
GitHub用于处理 Zoom Scribe 上传或存储媒体的转录流水线。涵盖媒体源确认、凭证设置、数据分块与重试机制设计，以及批量/快速模式实现和调试指南。适用于非实时会议场景的音频转录任务。
Trigger Scenarios
需要转录已上传或存储的媒体文件
配置 Zoom Scribe 批量或快速转录流水线
处理 Zoom AI Services 的异步转录回调
Install
npx skills add openai/plugins --skill scribe -g -y
SKILL.md
Frontmatter
{
"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
- Confirm the media source, size, language, expected latency, and whether fast mode or batch mode fits.
- Set up Build-platform credentials and JWT handling separately from application transcription logic.
- Design ingestion, chunking, retries, webhook callbacks, and persistence before connecting downstream AI workflows.
- Implement a minimal transcription request and response parser, then add batching and operational monitoring.
- Debug by checking credential audience, processing mode, media format, file size, backend timeout, and webhook delivery.
References
- Full preserved guide: references/full-guide.md
- Auth and processing modes: concepts/auth-and-processing-modes.md
- High-level scenarios: scenarios/high-level-scenarios.md
- Fast mode Node example: examples/fast-mode-node.md
- Batch webhook pipeline: examples/batch-webhook-pipeline.md
- API reference: references/api-reference.md
- Common drift and breaks: troubleshooting/common-drift-and-breaks.md
Version History
- 11c74d6 Current 2026-07-19 09:54
