CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-document-intelligence-java

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

55

Quality

63%

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-java/SKILL.md

The canonical home for this skill is azure-ai-document-intelligence-java 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.

A strong, executable Azure Document Intelligence Java reference with comprehensive code examples, though it is a monolithic single-file reference lacking validation checkpoints in its workflows and any progressive-disclosure file split.

Suggestions

Add validation checkpoints into the analyze/build workflows, e.g. check the poller status or wrap getFinalResult() in error handling before processing results, and verify a custom model exists before deleting it.

Move the bulk of the API reference (custom model management, classification, field schemas) into a separate references file and keep SKILL.md as a concise overview with one-level-deep links.

Remove the redundant "When to Use" filler line and the Trigger Phrases section (which duplicates the description) to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is a lean, code-first reference that mostly assumes Claude's competence; minor fluff such as "When to Use: This skill is applicable to execute the workflow or actions described in the overview." could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready, executable Java covering installation, client creation, prebuilt and custom model analysis, classification, composition, and error handling across the common cases.

5 / 5

Workflow Clarity

Each pattern has a recognizable sequence (build client, begin analyze, get result, process), but no validation checkpoints are integrated — e.g., no poller status/error checks before consuming the result, and risky admin operations (build/compose/delete model) lack verification steps.

3 / 5

Progressive Disclosure

The content is well-organized with clear section headers, but ~340 lines of API reference and model-management detail are all inlined in SKILL.md with no bundle files or external references to split the bulk into.

3 / 5

Total

15

/

20

Passed

Description

53%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 clear and distinct, naming the specific Azure SDK and language, but it stays at a high-level action ("build applications") and lacks an explicit use-when trigger clause. It would benefit from listing concrete operations and adding trigger guidance.

Suggestions

Replace the generic "Build document analysis applications" with concrete operations, e.g. "Extract text, tables, and key-value pairs; analyze receipts/invoices; build and classify custom document models with the Azure AI Document Intelligence SDK for Java."

Add an explicit trigger clause, e.g. "Use when working with the Azure Document Intelligence SDK in Java or when extracting text/OCR data from PDFs, receipts, invoices, or ID documents."

Include natural synonyms and file extensions users would say ("OCR", "extract text from PDF", ".pdf", "receipt", "invoice") to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("document analysis") and the specific SDK/language, but the only action stated is the generic "Build document analysis applications" with no concrete operations like extract/OCR/classify.

3 / 5

Completeness

Clearly states 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 natural terms ("document analysis", "Document Intelligence", "Java") but omits common variations users would say such as "OCR", "extract text from PDF", or "receipt/invoice".

3 / 5

Distinctiveness Conflict Risk

The combination of a specific cloud SDK and language ("Azure AI Document Intelligence SDK for Java") carves a clear niche with only minor overlap risk against other Azure or Java document skills.

4 / 5

Total

13

/

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.