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.

referencesdocument-intelligencepreflight-and-diagnostics.md

≈963 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Document Intelligence input preflight and diagnostics

For Azure AI Document Intelligence (v4.0, API 2024-11-30 GA) local input/label preflight, v3-to-v4 migration errors, source Blob access and async Operation-Location polling. Do not use for Microsoft Foundry agent creation, model deployments or Foundry IQ knowledge bases (microsoft-foundry / foundry-iq).

Workflow

  1. Reuse supplied tier (F0 or S0), model ID (prebuilt-read, prebuilt-layout, domain prebuilts or custom), API version, route and HTTP status/apim-request-id. Never ask for keys/SAS tokens or paste document text/field values into chat.

  2. Check node --version (needs Node.js 22+). If missing/older, do not install unasked; use analysis without Node. Otherwise run the local inspector from <skill-directory>:

    node "<skill-directory>/scripts/inspect-document-input.mjs" --file "<local-doc>" --tier S0 --model-kind layout
    & node "<skill-directory>\scripts\inspect-document-input.mjs" --file "<local-doc>" --tier S0 --model-kind layout

    Add --labels "<file.labels.json>" (--ocr "<file.ocr.json>") for custom training checks. Bash and PowerShell launchers forward flags (0 report/--help, 1 file/JSON error, 2 usage error, 3 Node 22+ missing).

  3. Check contract alignment (2024-11-30):

Symptom Public contract check
404 Resource Not Found v4 uses /documentintelligence/documentModels/{modelId}:analyze?api-version=2024-11-30; v3 uses /formrecognizer/documentModels/... (2023-07-31). Confirm custom modelId exists in the same resource/region.
InvalidContent / InvalidContentDimensions / InvalidContentLength / UnsupportedContent Check detectedFormat vs extension (e.g. HTML error saved as .pdf), encryption, image dimensions (50x50–10000x10000 px) and size (F0 4 MB, S0 500 MB).
Office (DOCX/PPTX/XLSX) or HTML rejected Listed for prebuilt-read and prebuilt-layout, not domain prebuilts or custom extraction. Learn pages disagree for custom classification (--model-kind classifier warns). Office/HTML results have no bounding polygons or lines.
Only 2 pages returned F0 processes only the first 2 pages; up to 2,000 pages can be processed (pages selects a range).
ContentSourceNotAccessible / InvalidSasToken (urlSource) Verify SAS expiry and read permission without logging secrets, or the managed identity's storage role and firewall settings.
429 Too Many Requests Separate POST Analyze (S0 15 TPS, F0 1 TPS) from GET polling (S0 50 TPS); honor retry-after.
Custom training data Learn limits: template 50 MB/500 pages, neural 1 GB/50,000 pages. With --labels, duplicates, boxes outside 0..1 and overlaps are review signals only (no public labels.json schema).
  1. For permitted live checks, inspect az cognitiveservices account show (SKU, customSubdomainName, publicNetworkAccess, disableLocalAuth) and Azure Monitor metrics/logs. Missing MCP/CLI access never blocks offline preflight.

Report and sources

Separate observed facts (file bytes, dimensions, HTTP code, apim-request-id), bounded interpretation, and unknown items (server-side parsing, uncollected diagnostics). Passing local checks does not guarantee extraction quality.

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