CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-formrecognizer-java

Build document analysis applications using the Azure AI Document Intelligence SDK for Java.

58

Quality

67%

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 ./skills/azure-ai-formrecognizer-java/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 Java examples and clean section organization. Its weakness is the lack of explicit validation/verification steps and feedback loops for risky operations like custom model building and deletion.

Suggestions

Add validation checkpoints to model-building and deletion workflows (e.g., verify the built model's accuracy on sample documents before use, confirm a model ID exists before deleting, handle poller failures explicitly).

Introduce a feedback loop for analysis failures (begin -> poll -> if error, inspect HttpResponseException status/retry) rather than only a single catch example.

DimensionReasoningScore

Conciseness

The body is largely lean and example-driven with minimal conceptual padding, though the prebuilt-model table and several near-duplicate analyze snippets add some length that could be trimmed.

4 / 5

Actionability

It provides complete, copy-paste-ready Java code for client creation, layout/invoice/receipt/document analysis, custom model building, classification, and error handling, covering the common cases with executable snippets.

5 / 5

Workflow Clarity

The analyze pattern (begin -> poller -> getFinalResult) is shown repeatedly, but there are no explicit validation checkpoints or feedback loops for batch/destructive operations like model building or deletion, capping clarity at 3.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Installation, Client Creation, Prebuilt Models, Core Patterns, Custom Models, Classification, Error Handling); no bundle files are present so everything is inline, which is appropriate but keeps it from a 5.

4 / 5

Total

16

/

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 distinct, clearly naming the Azure AI Document Intelligence SDK for Java as its niche. Its main weakness is the missing 'Use when...' trigger guidance, which caps completeness and limits natural discoverability.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger phrases (e.g., 'Use when extracting text or tables from PDFs, analyzing invoices/receipts, or building custom document models with the Azure Document Intelligence Java SDK').

Include common natural keywords in the description itself (PDF extraction, OCR, invoices, receipts) so users' phrasing matches without relying on a separate trigger-phrases section.

DimensionReasoningScore

Specificity

It names the domain (Azure AI Document Intelligence SDK for Java) and concrete actions ('Build document analysis applications'), which is specific but limited to a single high-level action rather than a comprehensive list of concrete operations.

4 / 5

Completeness

It clearly states what the skill does ('Build document analysis applications using the Azure AI Document Intelligence SDK for Java') but contains no 'Use when...' trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

The description references 'document analysis' and 'Document Intelligence SDK', which are relevant but lean technical; common natural variations users might say (OCR, PDF extraction, receipts) are absent from the description itself.

3 / 5

Distinctiveness Conflict Risk

Naming the specific Azure Document Intelligence SDK for Java gives it a clear niche with minimal overlap risk against generic document skills, though the absence of explicit triggers leaves minor ambiguity.

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
sickn33/antigravity-awesome-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.