azure-ai-document-intelligence-ts

Extract text, tables, and structured data from documents using prebuilt and custom models.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-document-intelligence-ts/SKILL.md

The canonical home for this skill is azure-ai-document-intelligence-ts in sickn33/agentic-awesome-skills

Quality

Content

65%Weight 40%Scale 1-5

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 executable examples and a documented polling workflow, but it is weakened by repeated polling boilerplate, missing verification steps for batch build operations, and a monolithic single-file structure with no progressive disclosure.

Suggestions

Factor the repeated polling boilerplate into the existing "Polling Pattern" section and reference it from the per-model examples instead of restating it each time.

Add a validation/verification step to the build-custom-model and build-classifier workflows (e.g., test the trained model on a sample document before relying on it).

Move the full type reference and model catalog into a separate REFERENCE.md and link to it from SKILL.md to enable one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and avoids explaining concepts Claude already knows, but the same polling boilerplate (isUnexpected -> getLongRunningPoller -> pollUntilDone) is repeated across 7+ examples rather than factored out once, which is more than minor padding.	3 / 5
Actionability	Examples are fully executable, copy-paste TypeScript with real imports, API paths, and model IDs covering the common cases (URL/local analysis, invoice, receipt, list, build, classify).	5 / 5
Workflow Clarity	The "Polling Pattern" section gives a clear 5-step sequence with an explicit error-check checkpoint, but the batch model/classifier build operations have no verification or error-recovery feedback loop, which per the guidelines caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Section headers and the model table give good structure, but no bundle files exist and all detailed material (full API examples, type reference, model catalog) is inlined in one ~320-line file with no signaled references to deeper material.	3 / 5
	Total	14 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 states a clear third-person purpose with concrete extraction actions, but it lacks any explicit use-when trigger guidance and omits natural user keywords (PDF, invoice, OCR). It is competent but incomplete by this rubric's standards.

Suggestions

Add an explicit "Use when ..." clause naming concrete triggers (e.g., when the user mentions PDFs, invoices, receipts, OCR, or document extraction).

Include natural synonyms and file extensions users actually say (PDF, .pdf, invoice, receipt, OCR) to improve trigger_term_quality.

Mention the classify/build capabilities briefly so the description's coverage matches the skill body.

Dimension	Reasoning	Score
Specificity	"Extract text, tables, and structured data from documents using prebuilt and custom models" lists several concrete actions (text, tables, structured data) plus model types, but omits capabilities the skill also covers (classify, build models/classifiers), so it is not a 5.	4 / 5
Completeness	The "what" is clear (extract text/tables/structured data via prebuilt/custom models) but there is no "Use when..." trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It uses relevant keywords ("documents", "tables", "structured data") but lacks the natural terms users actually say (PDF, invoice, receipt, OCR, .pdf), missing common variations and synonyms.	3 / 5
Distinctiveness Conflict Risk	"prebuilt and custom models" gives it a recognizable niche distinct from generic document skills, but the broad word "documents" and absence of explicit triggers leave minor overlap risk, so not a 5.	4 / 5
	Total	14 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-document-intelligence-ts/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.