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:sickn33/antigravity-awesome-skills --skill azure-ai-document-intelligence-ts96
Does it follow best practices?
Validation for skill structure
Evaluation results
92%
7%Accounts Payable Invoice Extractor
Local invoice data extraction
Correct SDK package
100%
100%
Client as function
100%
100%
isUnexpected error check
100%
100%
getLongRunningPoller usage
100%
100%
AnalyzeOperationOutput cast
37%
100%
base64 local file encoding
100%
100%
Correct analyze path pattern
100%
100%
Prebuilt invoice model
100%
100%
Field access pattern
75%
100%
Confidence score handling
0%
0%
Named imports
100%
100%
Without context: $0.3842 · 4m 9s · 22 turns · 29 in / 5,861 out tokens
With context: $0.4380 · 4m 3s · 23 turns · 291 in / 4,648 out tokens
92%
86%Custom Document Model Training Pipeline
Custom model training with neural mode
Correct SDK package
0%
100%
Client as function
0%
100%
isUnexpected error check
0%
100%
getLongRunningPoller for build
0%
100%
Neural build mode
0%
100%
azureBlobSource with containerUrl
0%
100%
Blob prefix field
0%
0%
Correct build path
0%
100%
Model ID in build body
25%
100%
Progress monitoring
50%
100%
Named imports
0%
100%
Without context: $0.3490 · 3m 37s · 21 turns · 27 in / 5,331 out tokens
With context: $0.6040 · 5m 21s · 28 turns · 65 in / 7,941 out tokens
100%
94%Intelligent Document Routing System
Document classification and routing
Correct SDK package
0%
100%
Client as function
0%
100%
isUnexpected on classifier build
0%
100%
isUnexpected on classify call
0%
100%
getLongRunningPoller for build
0%
100%
getLongRunningPoller for classify
0%
100%
DocumentClassifierBuildOperationDetailsOutput cast
0%
100%
Classifier analyze path
0%
100%
split: auto parameter
0%
100%
Classifier build path
0%
100%
docTypes with azureBlobSource
50%
100%
Without context: $1.0513 · 9m 46s · 50 turns · 59 in / 13,246 out tokens
With context: $0.6380 · 5m 44s · 33 turns · 299 in / 7,473 out tokens
- Evaluated
- Agent
- Claude Code
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.