azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building cu...
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill azure-ai-document-intelligence-ts95
Quality
96%
Does it follow best practices?
Impact
94%
2.93xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-document-intelligence-ts/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 specifies the technology (Azure Document Intelligence), concrete actions (extract text, tables, structured data), and explicit trigger scenarios (invoices, receipts, IDs, forms). The description uses proper third-person voice and includes both technical identifiers and natural user terms. The only minor issue is the truncation ('building cu...') which suggests the full description may contain additional context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extract text, tables, and structured data from documents' with a specific technology mentioned (@azure-rest/ai-document-intelligence). | 3 / 3 |
Completeness | Clearly answers both what ('Extract text, tables, and structured data from documents using Azure Document Intelligence') and when ('Use when processing invoices, receipts, IDs, forms, or building cu...'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'invoices', 'receipts', 'IDs', 'forms', 'documents', and the specific Azure service name for technical users. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Azure Document Intelligence service reference and the enumerated document types (invoices, receipts, IDs, forms), making it clearly distinguishable from generic document processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and conciseness. The code examples are complete, properly typed, and follow consistent patterns for error handling and async operations. The main weakness is that the content could be better organized with progressive disclosure - separating advanced features like custom model building and classifiers into linked reference files.
Suggestions
Consider splitting custom model building and classifier sections into a separate ADVANCED.md file, keeping SKILL.md focused on common prebuilt model usage
Add a brief 'Quick start' section at the top with the minimal code to analyze a document, before diving into authentication options
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing executable code examples without unnecessary explanations of what Azure Document Intelligence is or how REST APIs work. Every section delivers actionable information. | 3 / 3 |
Actionability | All code examples are fully executable TypeScript with proper imports, error handling, and type annotations. The examples are copy-paste ready and cover the full workflow from authentication to result extraction. | 3 / 3 |
Workflow Clarity | The polling pattern section explicitly documents the 5-step async workflow with numbered steps and error checking. The pattern is consistently applied across all examples with isUnexpected() checks before proceeding. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a long monolithic file (~200 lines) that could benefit from splitting advanced topics (custom models, classifiers) into separate reference files. The prebuilt models table is appropriately inline. | 2 / 3 |
Total | 11 / 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.