Index of every page on this site: llms.txt
All skills
microsoft avatar

/azure-ai

@0d60658
by microsoftmicrosoft/skills3.2k stars
373
Run it yourself

Build and troubleshoot Azure AI Search, Speech, Document Intelligence, Content Understanding, Translator, Content Safety, and OpenAI apps. WHEN: AI Search, vector search, hybrid search, semantic search, indexer, speech-to-text, text-to-speech, fast or batch transcription, Speech SDK logs, session ID, result ID, OCR, document translation, glossary.

Use this Skill: https://skilld.dev/gh/microsoft/skills/azure-ai

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencestranslatordocument-translation-preflight.md

≈987 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Translator Document Translation and glossary preflight

For Azure AI Translator Document Translation (async batch and sync single-file), glossary validation and Blob storage authorization. Do not use for Microsoft Foundry project connections (microsoft-foundry).

Workflow

  1. Confirm mode (async batch vs sync single-file vs Text API), tier (S1 or C2-C4/D3 required for Document Translation; F0 is Text API only) and auth (Managed Identity vs SAS). Never ask for keys/SAS or echo document/glossary text.

  2. Check node --version (Node.js 22+). If missing/older, follow validation without Node. Otherwise run the local validator:

    node "<skill-directory>/scripts/validate-document-translation.mjs" --mode async --dir "<source-folder>" --glossary "<glossary.tsv>" --target-count 2
    & node "<skill-directory>\scripts\validate-document-translation.mjs" --mode async --dir "<source-folder>" --glossary "<glossary.tsv>" --target-count 2

    Or pass --document "<file>". Bash and PowerShell launchers use exit codes 0 report/--help, 1 file error, 2 usage error, 3 Node 22+ missing.

  3. Verify documented limits and authorization rules:

Area Public contract
Async batch Document <= 40 MB (preview image .jpeg/.png/.bmp/.webp <= 5 MB on 2025-12-01-preview), <= 1,000 files, <= 250 MB batch total, <= 10 target languages, glossary <= 10 MB. Secured documents (password-encrypted or copy-restricted) can't be translated.
Sync single-file Document <= 10 MB, 1 file, 1 target language, glossary <= 1 MB. Formats: txt, tsv/tab, csv, html/htm, mhtml/mht, docx, xlsx, pptx, msg, xlf.
Formats GET /translator/document/formats (?type=glossary) is authoritative; validator list misses only warn.
Text API <= 50,000 chars/request across all target languages, <= 1,000 elements; sliding hourly quota (F0 2M/hr ≈ 33.3K/min, S1 40M/hr, Custom 3,600 chars/sec/model).
Glossary .tsv/.tab/.csv or .xlf. Partial-sentence matching is case-sensitive; full-sentence matching is case-insensitive.
Endpoint Requires custom domain https://<custom>.cognitiveservices.azure.com.
Managed Identity Translator must be in a geographic region (not Global) with a system-assigned identity. Assign Storage Blob Data Contributor at storage scope, omit SAS query strings, and on firewalled storage allow trusted Azure services plus a Microsoft.CognitiveServices/accounts resource-instance rule (up to 5 min to propagate).
SAS fallback Source rl, target wl, glossary rl, valid expiry.
  1. For permitted live checks, inspect az cognitiveservices account show (location, sku.name, properties.customSubdomainName, identity.type) and storage RBAC/firewall without listing keys.

Report and sources

Separate observed defects (row numbers, byte sizes, HTTP error codes), bounded interpretation, and unknown items. Passing local validation does not guarantee server translation accuracy.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning11d4 checks · Risk SAFE
  • Gen Agent Trust Hub11d

    This skill provides tools and guidance for developing and troubleshooting Azure AI services. It includes a local diagnostic script for analyzing Speech SDK logs with robust safety controls, along with comprehensive references for official Azure SDKs and secure authentication practices.

  • Socket11d

    No alerts

  • Snyk11d

    Risk: LOW · No issues

  • Runlayer9mo

    15/15 files flagged

Signed by skilld at 0d60658. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago
metadata
{
  "author": "Microsoft",
  "version": "1.2.6"
}

README badge

README badge for microsoft/skills/azure-ai