azure-ai-formrecognizer-java
Build document analysis applications with Azure Document Intelligence (Form Recognizer) SDK for Java. Use when extracting text, tables, key-value pairs from documents, receipts, invoices, or buildi...
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill azure-ai-formrecognizer-java92
Quality
89%
Does it follow best practices?
Impact
97%
1.21xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-formrecognizer-java/SKILL.mdDiscovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the specific Azure service, SDK language, and concrete use cases. It includes explicit 'Use when' guidance with natural trigger terms covering document types (receipts, invoices) and extraction targets (text, tables, key-value pairs). The description is truncated but the visible portion demonstrates excellent structure.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'extracting text, tables, key-value pairs from documents, receipts, invoices' and mentions building applications with a specific SDK. | 3 / 3 |
Completeness | Clearly answers both what ('Build document analysis applications... extracting text, tables, key-value pairs') and when ('Use when extracting text, tables, key-value pairs from documents, receipts, invoices'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Azure Document Intelligence', 'Form Recognizer', 'SDK for Java', 'documents', 'receipts', 'invoices', 'text', 'tables', 'key-value pairs'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Azure Document Intelligence, Form Recognizer, Java SDK) that clearly differentiates it from generic document processing or other cloud provider skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable SDK reference with excellent code examples that are immediately executable. The main weaknesses are the lack of validation workflows for multi-step operations (custom model building, classification training) and the monolithic structure that could benefit from splitting advanced topics into separate files.
Suggestions
Add validation checkpoints for custom model building workflow (e.g., verify training data format before building, check model status, validate with test documents before production use)
Include confidence threshold guidance and error recovery patterns when document analysis returns low confidence scores
Consider splitting Custom Models and Document Classification sections into separate reference files with a brief overview in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing executable code examples without explaining basic concepts Claude already knows. Every section serves a clear purpose with minimal filler text. | 3 / 3 |
Actionability | All code examples are fully executable Java with proper imports, complete method calls, and realistic usage patterns. Examples are copy-paste ready with clear placeholders for credentials. | 3 / 3 |
Workflow Clarity | While individual operations are clear, the skill lacks explicit validation checkpoints for multi-step processes like building custom models. No feedback loops for error recovery when training fails or when document analysis returns low confidence results. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic file with ~300 lines of code examples. Advanced topics like custom models and classification could be split into separate reference files for better navigation. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.