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.

57

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 complete, executable C# examples for every core workflow, and is reasonably well-organized. Its weaknesses are redundancy across overlapping reference tables, missing validation checkpoints in long-running model-build workflows, and lack of internal file splitting despite the skill's size.

Suggestions

Add explicit validation/verification checkpoints after long-running operations (e.g., check operation status or HasValue, verify model build succeeded before listing fields, retry on failure).

Consolidate the overlapping Client Types, Key Types Reference, and Related SDKs tables to remove redundancy and the repeated install command.

Split the dense Key Types Reference and per-model details into a separate references file (e.g., REFERENCE.md) and link to it from the overview.

DimensionReasoningScore

Conciseness

Mostly reference-style and code-heavy with minimal concept padding, but redundant tables (Client Types vs Key Types vs Related SDKs, repeated install info) and a verbatim repeat of the frontmatter intro could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready C# code across all seven workflows plus concrete install commands and real type/method names.

3 / 3

Workflow Clarity

Seven numbered workflows with clear sequencing and a try/catch error example exist, but long-running build/train operations lack explicit post-completion validation or feedback-loop checkpoints, capping clarity at 2.

2 / 3

Progressive Disclosure

Well-sectioned single-file skill with clearly signaled external reference links, but ~330 lines of dense API/type reference is inlined rather than split into a separate reference file, fitting the 'content that should be separate is inline' anchor.

2 / 3

Total

9

/

12

Passed

Description

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 specific and distinct, naming concrete extraction actions and a clear Azure/.NET niche, but it omits explicit 'when to use' trigger guidance and common user-facing document-type terms. Adding a 'Use when...' clause with terms like PDF, invoice, receipt, and forms would raise the trigger and completeness dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs to extract text, tables, or fields from PDFs, invoices, receipts, or scanned documents in .NET.'

Include natural trigger terms users actually say (PDF, invoice, receipt, OCR, forms, .pdf) rather than only generic 'documents' and 'models'.

Tie the prebuilt/custom distinction to concrete scenarios (e.g., 'Use prebuilt models for invoices/receipts, custom models for specialized forms').

DimensionReasoningScore

Specificity

Lists multiple concrete actions (extract text, tables, structured data) and distinguishes prebuilt vs custom models, matching the comprehensive-actions anchor.

3 / 3

Completeness

Clearly states what the skill does but lacks any 'Use when...' trigger clause, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains relevant keywords ('documents', 'text', 'tables', 'models') but omits natural terms users would say like 'PDF', 'invoice', 'receipt', 'OCR', or 'forms'.

2 / 3

Distinctiveness Conflict Risk

Names a specific Azure .NET SDK with a distinct niche (prebuilt/custom document models), making it unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

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
boisenoise/skills-collections
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.