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

Quality

Content

57%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 body delivers strong, executable C# examples across all major SDK operations with clean section structure. Weaknesses center on inlined reference material that belongs in separate files, missing validation around destructive operations, and a few boilerplate/time-sensitive sections that waste tokens.

Suggestions

Move the Key Types Reference, Build Modes, and advanced workflows (custom model build, classifier, model management) into reference files, keeping SKILL.md as a quick-start overview with clearly signaled one-level-deep links.

Add a validation step before destructive operations, e.g. confirm the model ID via GetModelAsync and its usage before DeleteModelAsync, and check operation.HasCompleted / field Confidence before consuming results.

Delete the generic "When to Use" and "Limitations" boilerplate and the pinned "Current Version: v1.0.0 (GA)" line, which add tokens without actionable value.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code and tables, but the time-sensitive "Current Version: v1.0.0 (GA)" line, the boilerplate "When to Use"/"Limitations" sections, and client types duplicated in both "Client Types" and "Key Types Reference" tables could all be trimmed.	3 / 5
Actionability	Seven workflows with concrete, mostly copy-paste-ready C# covering the common cases, plus install commands and auth snippets; minor gaps include undefined variables (receiptUri, documentUri in later workflows) and no local-file/stream analysis example.	4 / 5
Workflow Clarity	Workflows are clearly numbered and sequenced, but there are no validation checkpoints, and workflow 7 calls DeleteModelAsync (destructive) with no verification step, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	A single ~340-line file with good section headers, but the inlined Key Types/Build Modes reference tables and advanced workflows (4-7) are content that clearly belongs in separate reference files; no bundle files exist to offload it.	3 / 5
	Total	13 / 20 Passed

Description

70%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 specific, well-scoped description with concrete actions and a distinct SDK niche. Its main weakness is the missing "Use when..." trigger clause and the absence of natural document-type terms (PDF, invoice, receipt, OCR) that users would likely say.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with Azure Document Intelligence, or when extracting text, tables, or fields from PDFs, invoices, receipts, or forms in .NET".

Include common document-type synonyms (PDF, invoice, receipt, W-2, business card, OCR) so natural user phrasings match the description.

Mention classification and custom model building to round out capability coverage now that the description only lists extraction.

Dimension	Reasoning	Score
Specificity	"Extract text, tables, and structured data" names three concrete actions plus the prebuilt/custom model distinction, but omits capabilities the skill actually covers (classification, model building, invoices/receipts/IDs), leaving minor coverage gaps.	4 / 5
Completeness	The "what" is clear (extract text, tables, structured data via prebuilt and custom models), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	"Azure AI Document Intelligence", "extract text", "tables", and "documents" are natural user phrasings, but common terms like "PDF", "invoice", "receipt", "form", and "OCR" are absent.	4 / 5
Distinctiveness Conflict Risk	Naming the exact SDK ("Azure AI Document Intelligence SDK for .NET") carves out a clear niche with minimal overlap risk against generic document-processing skills.	5 / 5
	Total	16 / 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: 690de8f

Reviewed: 9 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.