CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-document-intelligence-dotnet

Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models. Use for invoice processing, receipt extraction, ID document analysis, and custom document models. Triggers: "Document Intelligence", "DocumentIntelligenceClient", "form recognizer", "invoice extraction", "receipt OCR", "document analysis .NET".

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable SDK reference with executable examples across all common workflows, but it is a monolithic single file with no progressive disclosure and lacks validation checkpoints around destructive operations.

Suggestions

Move the Prebuilt Models table, Key Types Reference, and full workflow code examples into separate reference files (e.g. references/models.md, references/workflows.md) linked from a concise overview, to improve progressive disclosure.

Add a validation/confirmation checkpoint before destructive calls such as DeleteModelAsync (e.g. confirm the model ID exists via GetModelAsync and prompt before deletion).

Relocate the time-sensitive 'Current Version: v1.0.0 (GA)' into a versioned/deprecated section or remove it so the body stays evergreen.

DimensionReasoningScore

Conciseness

The body is mostly lean reference material — tables and executable code with no padding about concepts Claude already knows — though the inline 'Current Version: v1.0.0 (GA)' is time-sensitive information not placed in a deprecated/old-patterns section.

4 / 5

Actionability

Seven full, copy-paste-ready workflows (invoice, layout, receipt, custom model, classifier, classify, manage) plus auth and error handling cover the common cases with executable code.

5 / 5

Workflow Clarity

Workflows are numbered and individually clear, but there are no validation checkpoints or feedback loops, and the destructive 'DeleteModelAsync' appears without any verification step, capping this dimension at 3.

3 / 5

Progressive Disclosure

No bundle files exist and the ~340-line body is monolithic — the Key Types, Prebuilt Models, and full workflow code that could live in one-level-deep reference files are all inlined, despite clear section headers.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states capabilities, use cases, and trigger terms with good synonym coverage. It fully answers what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Extract text, tables, and structured data', 'invoice processing', 'receipt extraction', 'ID document analysis', 'custom document models' — with comprehensive coverage of the SDK's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (extract text/tables/structured data via prebuilt and custom models) and 'when' ('Use for invoice processing, receipt extraction...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Triggers:' clause covers natural terms including the legacy synonym 'form recognizer', 'invoice extraction', 'receipt OCR', and the type name 'DocumentIntelligenceClient', giving comprehensive keyword coverage.

5 / 5

Distinctiveness Conflict Risk

Scoped to 'Azure AI Document Intelligence SDK for .NET' with distinct triggers, giving it a clear niche and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.