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.
77
66%
Does it follow best practices?
Impact
100%
1.35xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-document-intelligence-dotnet/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly identifying the Azure AI Document Intelligence SDK for .NET and listing concrete extraction capabilities. However, it lacks an explicit 'Use when...' clause and misses common trigger terms users might naturally use (e.g., 'OCR', 'Form Recognizer', 'C#'), which limits its effectiveness for skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to extract data from documents using Azure AI Document Intelligence, Form Recognizer, or Azure cognitive services in a .NET/C# project.'
Include common trigger term variations such as 'OCR', 'Form Recognizer' (the former product name), 'C#', 'document parsing', and file extensions like '.pdf', '.tiff', '.jpg' to improve matching against natural user queries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extract text, tables, and structured data from documents' and specifies the technology stack ('Azure AI Document Intelligence SDK for .NET') along with model types ('prebuilt and custom models'). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (extract text, tables, structured data using Azure AI Document Intelligence SDK for .NET), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Azure AI Document Intelligence', '.NET', 'extract text', 'tables', 'structured data', and 'documents', but misses common user variations like 'OCR', 'form recognizer', 'C#', 'document parsing', or file type extensions like '.pdf', '.jpg'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Azure AI Document Intelligence SDK' and '.NET' creates a very clear niche that is unlikely to conflict with generic document processing skills or other cloud provider SDKs. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable SDK reference with excellent executable code examples covering the full range of Azure Document Intelligence operations. Its main weaknesses are its length (could benefit from splitting detailed workflows into separate files) and the lack of validation/verification steps in workflows that involve building custom models or processing documents at scale. The content is mostly efficient but has some unnecessary sections like the boilerplate 'When to Use' and the deprecated SDK mention.
Suggestions
Add validation checkpoints to workflows, especially for custom model building (e.g., verify training data format, check model accuracy metrics after build, validate results before proceeding).
Split detailed workflows (custom model building, classifier, model management) into a separate WORKFLOWS.md file, keeping SKILL.md as a concise overview with the most common operations (analyze invoice, extract layout).
Remove the boilerplate 'When to Use' section and the 'Related SDKs' table mentioning the deprecated SDK — these waste tokens without adding actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary content like the 'When to Use' boilerplate at the end, the 'Related SDKs' section mentioning the deprecated SDK, and some verbose inline comments. The prebuilt models table and key types reference table could be trimmed since Claude can infer many of these. However, the code examples are reasonably tight and the tables are useful reference material. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready C# code examples for all major workflows including invoice analysis, layout extraction, receipt analysis, custom model building, classification, and model management. Code includes proper imports, error handling, and field extraction patterns with confidence checking. | 3 / 3 |
Workflow Clarity | The workflows are presented as numbered sections with clear code, but they lack validation checkpoints and error recovery feedback loops. For example, the custom model building workflow doesn't include steps to validate training data or verify model quality after building. The analyze workflows don't mention checking for empty results or handling partial failures. Each workflow is essentially 'call API, read results' without verification steps. | 2 / 3 |
Progressive Disclosure | The content is a long monolithic file (~300 lines) with no references to external files for detailed content. The prebuilt models table, key types reference, and some of the more specialized workflows (classifier building, model management) could be split into separate reference files. However, the section headers provide reasonable navigation within the single file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- boisenoise/skills-collections
- Commit
f1697b6
- 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.