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.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-azure-ai-document-intelligence-dotnet/SKILL.md

The canonical home for this skill is azure-ai-document-intelligence-dotnet in sickn33/antigravity-awesome-skills

Quality

Content

68%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.

The content is highly actionable with comprehensive executable C# examples and good structural organization, but it carries time-sensitive version info and a placeholder 'When to Use' section, and its build/manage workflows lack explicit validation checkpoints. Tightening the version framing and adding verify steps would raise the weaker dimensions.

Suggestions

Move or frame 'Current Version: v1.0.0 (GA)' within a versioning/deprecated note so time-sensitive info does not penalize conciseness, and replace the generic 'When to Use' placeholder with concrete triggers.

Add validation checkpoints to the build-model and manage-models workflows (e.g. poll operation status, verify model is ready before listing/deleting, confirm classifier accuracy on a held-out sample).

Wire the error-handling try/catch pattern into the long-running operation examples as an explicit validate-then-retry feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code and tables, but time-sensitive info ('Current Version: v1.0.0 (GA)') sits outside a deprecated section and the generic 'When to Use' placeholder ('This skill is applicable to execute the workflow or actions described in the overview.') adds padding.	3 / 5
Actionability	Seven fully executable, copy-paste-ready C# workflows (analyze invoice, layout, receipt, build model, classifier, classify, manage models) cover the common cases with concrete APIs and field access patterns.	5 / 5
Workflow Clarity	The recipes are clear individual actions but lack validation checkpoints or feedback loops for long-running/build operations; the error-handling example is isolated rather than wired into the build and manage workflows.	3 / 5
Progressive Disclosure	No bundle files exist, so all content is inline, but the single file is well-organized with clear section headers and a Reference Links table pointing one level deep to external docs, NuGet, and GitHub samples.	4 / 5
	Total	15 / 20 Passed

Description

58%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.

The description clearly states what the SDK does and is reasonably specific and distinctive, but it omits any 'when to use' trigger guidance and lacks natural file-type synonyms users would mention. Adding an explicit Use-when clause would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when extracting text, tables, or fields from PDFs, scanned forms, invoices, or receipts in .NET, or when building custom document models.'

Add natural user-facing terms and file extensions (PDFs, .pdf, invoices, receipts, forms) to improve trigger-term coverage.

Mention classification alongside extraction to broaden the specificity of capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Document Intelligence SDK for .NET') and several concrete actions ('Extract text, tables, and structured data from documents using prebuilt and custom models'), with only minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant keywords like 'documents' and 'extract text, tables, and structured data', but misses common natural variations and file extensions (.pdf, .docx) or document types (invoices, receipts, forms) users actually say.	3 / 5
Distinctiveness Conflict Risk	The specific SDK name and '.NET' language pin a clear niche with minimal conflict risk, though there is minor overlap with the legacy Azure.AI.FormRecognizer SDK.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-azure-ai-document-intelligence-dotnet/SKILL.md
Commit: 19c310e

Reviewed: about 17 hours ago

Table of Contents

Discovery Implementation Validation

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.