跳到正文
cccskills
免费在 GitHub 公开

scribe

Build transcription workflows for uploaded or stored audio and video using Zoom AI Services Scribe. Consult guidance on authentication, single-file requests, batch jobs, completion notifications, and saving transcript results for further processing.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Reference skill for Zoom AI Services Scribe. Use after routing to a transcription workflow when handling uploaded or stored media, Build-platform JWT auth, fast mode transcription, batch jobs, or transcript pipeline design.

集成工具Zoom
查看安装方法

适用场景

  • Adding transcription for uploaded recordings
  • Transcribing stored call archives in batches
  • Saving transcripts after job completion notifications
  • Investigating browser timeouts during transcription

包含的文件(11)

  • SKILL.md5.8 KB
  • concepts/auth-and-processing-modes.md3.2 KB
  • examples/batch-webhook-pipeline.md1.6 KB
  • examples/fast-mode-node.md1.8 KB
  • references/api-reference.md2.6 KB
  • references/environment-variables.md1.5 KB
  • references/samples-validation.md2.0 KB
  • references/versioning-and-drift.md2.0 KB
  • RUNBOOK.md4.2 KB
  • scenarios/high-level-scenarios.md3.1 KB
  • troubleshooting/common-drift-and-breaks.md4.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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.

Quick Links

  1. concepts/auth-and-processing-modes.md
  2. scenarios/high-level-scenarios.md
  3. examples/fast-mode-node.md
  4. examples/batch-webhook-pipeline.md
  5. references/api-reference.md
  6. references/environment-variables.md
  7. references/samples-validation.md
  8. references/versioning-and-drift.md
  9. troubleshooting/common-drift-and-breaks.md
  10. RUNBOOK.md

Core Workflow

  1. Get Build-platform credentials and generate an HS256 JWT.
  2. Choose fast mode for one short file or batch mode for stored archives / large sets.
  3. Submit the transcription request.
  4. For batch jobs, poll job/file status or receive webhook notifications.
  5. Persist and post-process transcript JSON.

Hosted Fast-Mode Guardrail

  • The formal fast-mode API limits are 100 MB and 2 hours, but hosted browser flows can still time out before the upstream response returns.
  • Current deployed-sample observations:
    • ~17.2 MB MP4 completed in about 26s
    • ~38.6 MB MP4 completed in about 26-37s
    • ~59.2 MB MP4 completed in about 32-34s on the backend
    • some ~59.2 MB browser requests still surfaced as frontend 504 while backend logs later showed 200
  • Treat frontend 504 plus backend 200 as a browser/edge timeout race, not an automatic transcription failure.
  • For hosted UIs, prefer an async request/polling wrapper for fast mode instead of holding the browser open for the full upstream response.
  • For larger or less predictable media, prefer batch mode even when the file is still within the formal fast-mode size limit.

Browser Microphone Pattern

  • scribe does not expose a documented real-time streaming API surface.
  • If you want a browser microphone experience, use pseudo-streaming:
    1. capture microphone audio in short chunks
    2. upload each chunk through the async fast-mode wrapper
    3. poll for completion
    4. append chunk transcripts in sequence
  • Recommended starting cadence:
    • chunk size: 5 seconds
    • acceptable range: 5-10 seconds
    • in-flight chunk requests: 2-3
  • This is a practical UI pattern for incremental transcript updates, not a substitute for rtms.
  • Treat this as a fallback demo pattern, not the preferred production architecture.
  • It adds repeated upload overhead, chunk-boundary drift, browser codec/container variability, and transcript stitching complexity.
  • If the user asks for actual live stream ingestion, low-latency continuous media, or server-push media transport, route to ../rtms/SKILL.md instead.

Endpoint Surface

ModeMethodPathUse
FastPOST/aiservices/scribe/transcribeSynchronous transcription for one file
BatchPOST/aiservices/scribe/jobsSubmit asynchronous batch job
BatchGET/aiservices/scribe/jobsList jobs
BatchGET/aiservices/scribe/jobs/{jobId}Inspect job summary/state
BatchDELETE/aiservices/scribe/jobs/{jobId}Cancel queued/processing job
BatchGET/aiservices/scribe/jobs/{jobId}/filesInspect per-file results

High-Level Scenarios

  • On-demand clip transcription after a user uploads one recording.
  • Batch transcription of stored S3 call archives.
  • Webhook-driven ETL pipeline that writes transcripts to your database/search index.
  • Re-transcription of Zoom-managed recordings after exporting them to your own storage.
  • Offline compliance or QA workflows that need timestamps, channel separation, and speaker hints.

Chaining

Operations

  • RUNBOOK.md - 5-minute preflight and debugging checklist.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Review a design or web page against WCAG 2.1 AA, an accessibility standard. Organize findings on contrast, keyboard access, forms, and screen reader behavior, with severity levels and practical recommendations for fixes.

中文简介正在准备中。当前显示英语简介。

  • Review accessibility before design handoff
  • Check text and interface color contrast
  • Review keyboard navigation and focus behavior
anthropics/knowledge-work-plugins3万2026年10月17日 更新

Build a single brief on an existing customer using available sales records, emails, documents, call notes, and internal chat. Understand the current situation, key contacts, recent discussions, and gaps that may need attention.

中文简介正在准备中。当前显示英语简介。

  • Preparing for a meeting with an existing customer
  • Catching up on an account during a handover
  • Reviewing recent discussions and stalled opportunities
anthropics/knowledge-work-plugins3万2026年10月17日 更新

Build or refresh a strategic customer account plan from sales records, emails, and meeting transcripts. Organize goals, stakeholders, growth opportunities, risks, and dated actions into a document, then sync approved highlights to the customer relationship management system.

中文简介正在准备中。当前显示英语简介。

  • Creating a quarterly plan for a key customer
  • Refreshing an existing account plan
  • Reviewing stakeholder coverage and growth opportunities
anthropics/knowledge-work-plugins3万2026年10月17日 更新

Research prospective companies and contacts, check existing customer records, and assess fit against your ideal customer profile. Receive a sourced brief covering recent developments, likely priorities, outreach talking points, and a suggested next step.

中文简介正在准备中。当前显示英语简介。

  • Researching a company before a sales approach
  • Checking existing account records and ownership
  • Assessing fit against your ideal customer profile
anthropics/knowledge-work-plugins3万2026年10月17日 更新

Research sales accounts using Common Room data to summarize company details, buying signals, ownership, and key contacts. Answer specific questions directly or prepare a broader briefing with evidence-based next steps, clearly identifying missing information.

中文简介正在准备中。当前显示英语简介。

  • Prepare a company briefing before a sales conversation
  • Check buying signals and recent account activity
  • Find account owners and key contacts
anthropics/knowledge-work-plugins3万2026年10月17日 更新

Score and group accounts by customer fit and engagement, such as recent contact and open sales opportunities. Identify where to focus sales effort, choose next actions, and spot promising accounts with neglected outreach or missing information.

中文简介正在准备中。当前显示英语简介。

  • Prioritize a portfolio of assigned accounts
  • Find strong-fit accounts that need outreach
  • Identify promising accounts with no recent activity
anthropics/knowledge-work-plugins3万2026年10月17日 更新

查看 anthropics 的全部技能

报告此技能的问题