azure-ai-formrecognizer-java

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 content is highly actionable with comprehensive, executable Java examples, but it is organized as a monolithic reference rather than a sequenced workflow with validation checkpoints, and it repeats patterns with some boilerplate filler.

Suggestions

Remove filler boilerplate (the restated title line and the generic 'When to Use'/'Limitations' sentences) to tighten token efficiency.

Add explicit validation/verification checkpoints after long-running poller operations such as building custom models and classifiers (e.g., check model status/accuracy before proceeding).

Split large reference sections (e.g., custom models, classification, administration) into separate reference files and link to them from the SKILL.md overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, code-forward content without conceptual padding about PDFs/OCR, but it repeats near-identical SyncPoller patterns and includes filler boilerplate sections ("When to Use: This skill is applicable to execute the workflow...", a restated title). Mostly efficient but could be tightened, so not a 3.	2 / 3
Actionability	Provides abundant concrete, executable Java with imports, real method names, and copy-paste-ready examples across client creation, prebuilt models, custom models, classification, and error handling. Fully executable and specific, matching the top anchor.	3 / 3
Workflow Clarity	Each pattern has a recognizable sequence, but content is organized as standalone recipes rather than a sequenced workflow, and long poller operations (custom model build, classifier build) lack explicit validation/verification checkpoints. Per scoring notes, missing feedback loops for these operations caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Everything lives in one monolithic SKILL.md with no bundle files in references/scripts/assets and no one-level-deep external references; API-reference-style content that could be split out is inline. Some section organization exists, but content is not appropriately split, so not a 3.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 to a clear niche and names the relevant SDK, but it is light on concrete action enumeration and lacks an explicit 'Use when' trigger clause. It is solid but leaves trigger guidance implicit.

Suggestions

Enumerate several concrete actions in the description (e.g., extract text/tables, analyze invoices and receipts, build custom models, classify documents) instead of the single phrase 'build document analysis applications'.

Add an explicit 'Use when...' clause listing natural triggers such as extracting text from PDFs, OCR, or analyzing invoices/receipts in Java.

Include common user phrasings (e.g., 'extract text from PDF', 'OCR document', 'analyze invoice') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Document Intelligence SDK for Java) and a general action ("build document analysis applications"), but does not enumerate multiple specific concrete actions like extracting text, tables, or forms. Not a 1 because it is not vague, not a 3 because it lists only one broad action.	2 / 3
Completeness	It states what the skill does but lacks an explicit "Use when..." trigger clause; per the judging guidelines a missing explicit trigger guidance caps completeness at 2. Has 'what' but 'when' is only implied.	2 / 3
Trigger Term Quality	Includes relevant terms ("document analysis", "Azure AI Document Intelligence", "Java") but omits natural phrases a user would say such as "extract text from PDF", "OCR", or "analyze invoices". Relevant keywords present but common variations missing, so not a 3.	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to the Azure AI Document Intelligence SDK for Java, a clear niche unlikely to trigger for unrelated skills. Clearly distinguishable, matching the anchor for a distinct niche.	3 / 3
	Total	9 / 12 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
Commit: f36337d

Reviewed: 2 days 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.