agentleFS
zoomzoom/skills/skills/translator/SKILL.md

translator

Skill82 starsChanged 8 months agoMITView on GitHub

Zoom AI Services Translator for synchronous text translation and asynchronous batch file translation. Use for plain-text translation, one-target-language jobs, S3 text archives, Build-platform JWT auth, and webhook-driven translation pipelines.

We split this skill into the rules it gives an agent

7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user needs plain text translated, route here first.

    line 38
  2. Very specific:

    If the user needs audio/video transcribed before translation, route to ../scribe/SKILL.md, then chain here.

    line 39
  3. Very specific:

    If the user needs summaries or action items, route to ../summarizer/SKILL.md.

    line 40
  4. Very specific:

    If the user needs live meeting media before translation, route to ../rtms/SKILL.md.

    line 41
  5. Very specific:

    If the user needs the raw AI Services endpoint inventory, chain ../rest-api/SKILL.md.

    line 42
  6. Very specific:

    If the user needs webhook signature patterns, optionally chain ../webhooks/SKILL.md.

    line 43
  7. Very specific:

    Use BCP-47 locale codes such as en-US and es-ES, not short codes such as en.

    line 92

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Zoom AI Services Translator

Current API audit: Official docs and OpenAPI were rechecked on 2026-07-10. The full fast, batch job, job-list/status/cancel, file-list, and per-file detail surface released May 18, 2026 is included below.

Implementation guidance for Zoom AI Services Translator across:

  • synchronous plain-text translation (POST /aiservices/translator/translate)
  • asynchronous batch text-file jobs (/aiservices/translator/jobs*)
  • one-target-language translation workflows
  • Build-platform JWT generation and server-side credential handling
  • webhook-driven batch status updates

Official docs:

Routing Guardrail

  • If the user needs plain text translated, route here first.
  • If the user needs audio/video transcribed before translation, route to ../scribe/SKILL.md, then chain here.
  • If the user needs summaries or action items, route to ../summarizer/SKILL.md.
  • If the user needs live meeting media before translation, route to ../rtms/SKILL.md.
  • If the user needs the raw AI Services endpoint inventory, chain ../rest-api/SKILL.md.
  • If the user needs webhook signature patterns, optionally chain ../webhooks/SKILL.md.

Quick Links

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

Core Workflow

  1. Get Build-platform API key and API secret.
  2. Generate an HS256 JWT server-side.
  3. Choose fast mode for one text string or batch mode for stored text files.
  4. Set source_language and a single target_languages entry.
  5. Submit the request and persist result.translations.
  6. For batch jobs, poll job/file status or receive webhook notifications.

Endpoint Surface

ModeMethodPathUse
FastPOST/aiservices/translator/translateSynchronous translation for one text input
BatchPOST/aiservices/translator/jobsSubmit asynchronous batch translation job
BatchGET/aiservices/translator/jobsList batch translation jobs
BatchGET/aiservices/translator/jobs/{jobId}Inspect job summary/state
BatchDELETE/aiservices/translator/jobs/{jobId}Cancel queued/processing job
BatchGET/aiservices/translator/jobs/{jobId}/filesInspect per-file results
BatchGET/aiservices/translator/jobs/{jobId}/files/{fileId}Inspect one per-file result

Mode Selection

NeedUse
One text value under 4,000 charactersFast mode
.txt files in S3Batch mode
Chat messages, UI strings, workflow actionsFast mode
Large offline document archiveBatch mode

Translation Guardrails

  • Fast mode supports one target language per request.
  • Batch mode supports one target language per job.
  • Translation is bidirectional with English: every job must have either source_language or target_languages set to en-US.
  • Non-English to non-English pairs are not supported yet.
  • Use BCP-47 locale codes such as en-US and es-ES, not short codes such as en.

Chaining

  • Media to transcript to translation -> ../scribe/SKILL.md + translator
  • Summary to localized output -> ../summarizer/SKILL.md + translator
  • Batch webhook receiver -> translator + ../webhooks/SKILL.md
  • Raw endpoint discovery -> ../rest-api/SKILL.md
  • Cross-product routing -> ../general/SKILL.md

Operations

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

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.

Reviews can't be read right now.

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.