sickn33/antigravity-awesome-skills/azure-ai-document-intelligence-dotnet
- community
Checking that the SKILL.md file is still in the repository.
Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models.
Install
npx vskill@latest install sickn33/antigravity-awesome-skills/azure-ai-document-intelligence-dotnetSKILL.md
Azure.AI.DocumentIntelligence (.NET)
Extract text, tables, and structured data from documents using prebuilt and custom models.
Installation
Current Version: v1.0.0 (GA)
Environment Variables
Authentication
Microsoft Entra ID (Recommended)
Note: Entra ID requires a custom subdomain (e.g.,https://<resource-name>.cognitiveservices.azure.com/), not a regional endpoint.
API Key
Client Types
| Client | Purpose | |
|---|---|---|
DocumentIntelligenceClient | Analyze documents, classify documents | |
DocumentIntelligenceAdministrationClient | Build/manage custom models and classifiers |
Prebuilt Models
| Model ID | Description | |
|---|---|---|
prebuilt-read | Extract text, languages, handwriting | |
prebuilt-layout | Extract text, tables, selection marks, structure | |
prebuilt-invoice | Extract invoice fields (vendor, items, totals) | |
prebuilt-receipt | Extract receipt fields (merchant, items, total) | |
prebuilt-idDocument | Extract ID document fields (name, DOB, address) | |
prebuilt-businessCard | Extract business card fields | |
prebuilt-tax.us.w2 | Extract W-2 tax form fields | |
prebuilt-healthInsuranceCard.us | Extract health insurance card fields |
Core Workflows
Confirm the resource region/tenant and permission to send document contents to Azure before analysis or training. IDs, invoices and health documents may be highly sensitive: use approved sample data, do not log extracted personal fields or SAS URLs, and scope short-lived storage access to the required container. Pin the SDK/API version and verify supported models/field types and overloads in matching official samples; fragments are not a compiled application. A confidence score is not verified accuracy: reconcile fields with source pages and business rules before decisions. Training/analysis can incur cost; deletion must target only explicitly authorized models.
1. Analyze Invoice
2. Extract Layout (Text, Tables, Structure)
3. Analyze Receipt
4. Build Custom Model
5. Build Document Classifier
6. Classify Document
7. Manage Models
Key Types Reference
| Type | Description | |
|---|---|---|
DocumentIntelligenceClient | Main client for analysis | |
DocumentIntelligenceAdministrationClient | Model management | |
AnalyzeResult | Result of document analysis | |
AnalyzedDocument | Single document within result | |
DocumentField | Extracted field with value and confidence | |
DocumentFieldType | String, Date, Number, Currency, etc. | |
DocumentPage | Page info (lines, words, selection marks) | |
DocumentTable | Extracted table with cells | |
DocumentModelDetails | Custom model metadata | |
BlobContentSource | Training data source |
Build Modes
| Mode | Use Case | |
|---|---|---|
DocumentBuildMode.Template | Fixed layout documents (forms) | |
DocumentBuildMode.Neural | Variable layout documents |
Best Practices
- Use DefaultAzureCredential for production
- Reuse client instances — clients are thread-safe
- Handle long-running operations — Use
WaitUntil.Completedfor simplicity - Check field confidence — Always verify
Confidenceproperty - Use appropriate model — Prebuilt for common docs, custom for specialized
- Use custom subdomain — Required for Entra ID authentication
Error Handling
Related SDKs
| SDK | Purpose | Install | |
|---|---|---|---|
Azure.AI.DocumentIntelligence | Document analysis (this SDK) | dotnet add package Azure.AI.DocumentIntelligence | |
Azure.AI.FormRecognizer | Legacy SDK (deprecated) | Use DocumentIntelligence instead |
Reference Links
| Resource | URL | |
|---|---|---|
| NuGet Package | https://www.nuget.org/packages/Azure.AI.DocumentIntelligence | |
| API Reference | https://learn.microsoft.com/dotnet/api/azure.ai.documentintelligence | |
| GitHub Samples | https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/documentintelligence/Azure.AI.DocumentIntelligence/samples | |
| Document Intelligence Studio | https://documentintelligence.ai.azure.com/ | |
| Prebuilt Models | https://aka.ms/azsdk/formrecognizer/models |
When to Use
This skill is applicable to execute the workflow or actions described in the overview.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/azure-ai-document-intelligence-dotnet/SKILL.md
Popularity
- Repository stars
- 32,484
- Repository forks
- 5,408
- Repository npm downloads, 7 days
- 11,088
- 7-day trend score
- 74
Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 13 Apr 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/sickn33/antigravity-awesome-skills/azure-ai-document-intelligence-dotnet)