azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using prebuilt and custom models.
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-azure-ai-document-intelligence-ts/SKILL.mdQuality
Discovery
60%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 does a good job listing specific extraction capabilities (text, tables, structured data) and hints at the method (prebuilt and custom models). However, it lacks an explicit 'Use when...' clause, uses the overly generic term 'documents' without specifying file types, and could conflict with other document-processing skills due to insufficient distinctiveness.
Suggestions
Add a 'Use when...' clause with explicit trigger conditions, e.g., 'Use when the user needs to extract text, tables, or fields from documents using AI/ML models, OCR, or form recognition.'
Include specific file types and natural user terms such as 'PDF, invoices, receipts, forms, OCR, scanned documents, .pdf, .tiff' to improve trigger term coverage and distinctiveness.
Clarify what 'prebuilt and custom models' refers to (e.g., Azure Document Intelligence, AWS Textract) to help distinguish this skill from simpler document parsing tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extract text, tables, and structured data' and mentions both 'prebuilt and custom models' as methods. This provides clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (extract text, tables, structured data from documents using models), but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'extract text', 'tables', 'structured data', and 'documents', but lacks specific file type keywords users would naturally say (e.g., PDF, invoice, receipt, OCR, .pdf, .docx) and misses common variations. | 2 / 3 |
Distinctiveness Conflict Risk | 'Documents' is quite broad and could overlap with many document-related skills. The mention of 'prebuilt and custom models' adds some distinctiveness but doesn't clearly carve out a niche compared to other document extraction tools. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with excellent actionability — all code examples are executable, properly typed, and cover the major use cases of the Azure Document Intelligence REST SDK. However, it suffers from repetitive patterns (the analyze→check→poll flow is repeated verbatim across many sections), generic boilerplate sections at the end, and could benefit from better progressive disclosure by extracting detailed examples into separate files. Adding error recovery guidance and validation steps for custom model building would improve workflow clarity.
Suggestions
Consolidate the repeated analyze→isUnexpected→poll pattern into a single documented helper, then reference it in subsequent examples to reduce redundancy.
Add error recovery guidance for common failure modes (polling timeout, invalid training data, quota exceeded) especially for the custom model build workflow.
Remove the generic 'When to Use' and 'Limitations' sections which add no skill-specific value, or replace them with concrete constraints (e.g., file size limits, supported formats, API version compatibility).
Consider splitting detailed examples (invoice, receipt, classifier) into a separate EXAMPLES.md file, keeping SKILL.md as a concise overview with the core pattern and model table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but there's significant repetition in the polling pattern (shown multiple times before being explicitly documented as a pattern), and the invoice/receipt examples are nearly identical boilerplate. The 'When to Use' and 'Limitations' sections are generic filler that add no value. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with correct imports, proper type annotations, and real API patterns. The examples cover authentication, URL/file analysis, prebuilt models, custom models, classification, and pagination — all copy-paste ready. | 3 / 3 |
Workflow Clarity | The polling pattern section clearly sequences the async workflow (start → check errors → create poller → monitor → wait), but there are no validation checkpoints for destructive operations like building custom models, no guidance on what to do when polling fails or times out, and no feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and a useful prebuilt models reference table, but it's a long monolithic file (~200+ lines of code examples) with no references to external files for advanced topics like custom model training details, field schemas, or error handling guides. The invoice and receipt examples could be consolidated or moved to a separate file. | 2 / 3 |
Total | 9 / 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 | |
- Repository
- boisenoise/skills-collections
- Commit
431bfad
- 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.