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.

56

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-document-intelligence-dotnet/SKILL.md

The canonical home for this skill is azure-ai-document-intelligence-dotnet in administrakt0r/AI-Agents-Safe-Coding-Skills

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.

The body is highly actionable, with executable C# examples across the main workflows, and is reasonably concise; its main weaknesses are missing validation/feedback loops around destructive model operations and no progressive disclosure into bundle files.

Suggestions

Add an explicit validation/verification checkpoint before destructive operations (e.g., confirm the model exists via GetModelAsync and require user confirmation before DeleteModelAsync), and a fix-and-retry loop for long-running build operations.

Move the bulk reference tables (Prebuilt Models, Key Types, Build Modes) into a bundled reference file linked from the body, so SKILL.md stays a lean overview that progressively discloses detail.

Trim the low-value 'When to Use' line and the single-row 'Related SDKs' table to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly lean executable code and compact tables that assume Claude's competence; it earns 4 rather than 5 because of minor trimmable filler such as the vague 'When to Use' line ('This skill is applicable to execute the workflow or actions described in the overview') and the single-row 'Related SDKs' table that duplicates the install command.

4 / 5

Actionability

It provides copy-paste-ready, executable C# covering the common cases (analyze invoice/receipt, layout extraction, build custom model/classifier, classify, manage models, error handling), matching the 'fully executable; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

Workflows are numbered and sequenced, but destructive and long-running operations like DeleteModelAsync and BuildDocumentModelAsync have no validation checkpoints or fix-and-retry feedback loops; the rubric explicitly caps workflow clarity at 3 for destructive/batch operations missing validation, so it cannot reach 4.

3 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and ~330 lines of content—including the prebuilt-models, key-types, and build-modes tables that could live in separate files—are inlined; external Reference Links are present, but the lack of in-bundle navigation and inline bulk content places it at the 'some structure, content that should be separate is inline' anchor rather than the well-split 4 anchor.

3 / 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 is specific and distinctive, naming concrete extraction actions within a clear Azure/.NET niche, but it omits any 'Use when...' trigger guidance and lacks common natural terms (PDF, OCR, forms) that users would actually say.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when extracting text, tables, or fields from PDFs/images, or when the user mentions OCR, invoices, receipts, or document analysis in .NET.'

Include natural user vocabulary such as 'PDF', 'OCR', 'forms', 'invoices', and 'receipts' alongside the SDK-oriented terms to improve trigger-term coverage.

DimensionReasoningScore

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, fitting the 'lists several specific actions' anchor above the 1-2-action midpoint.

4 / 5

Completeness

It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric, a missing when-clause caps completeness at 3, which is confirmed because it does not reach the 4 anchor's dual what-and-when structure.

3 / 5

Trigger Term Quality

It includes relevant keywords ('documents', 'text', 'tables', 'structured data') but misses the natural terms users actually say (PDF, OCR, forms, invoices, receipts, .pdf), so it sits at the 'some relevant keywords but missing common variations' anchor rather than the 4 anchor's broad coverage.

3 / 5

Distinctiveness Conflict Risk

The phrase 'Azure AI Document Intelligence SDK for .NET' carves out a specific niche with minimal conflict risk against unrelated skills; it stays at 4 rather than 5 only because no explicit distinct trigger phrases are given that would fully separate it from adjacent Azure/document skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.