azure-ai-textanalytics-py

Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP. Use for natural language processing on text.

1.56x

Quality

67%

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-textanalytics-py/SKILL.md

Quality

Content

76%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 body is exceptionally lean and highly actionable with copy-paste-ready code across all major operations. Its weaknesses are the absence of validation/error-recovery feedback loops for batch and long-running operations, and no progressive disclosure via separate reference files despite substantial inlined reference material.

Suggestions

Add explicit validation/feedback-loop steps for the long-running and batch operations, e.g. check poller.done() / poller.status(), and show retry/handling when a document result is_error is true rather than silently skipping.

Move the larger reference tables (Available Operations, Client Types) and detailed advanced sections into a separate reference file and link to it from SKILL.md, keeping the body as a lean overview.

Replace the filler 'When to Use' sentence ('This skill is applicable to execute the workflow or actions described in the overview.') with concrete usage guidance or remove it.

Dimension	Reasoning	Score
Conciseness	The body is lean and almost entirely code with minimal prose; it assumes Claude's competence and avoids explaining what the SDK or NLP concepts are, so every token earns its place.	5 / 5
Actionability	Provides copy-paste-ready executable code for every common operation (sentiment, entities, PII, key phrases, language, healthcare, batch actions, async), covering the common cases with concrete, complete snippets.	5 / 5
Workflow Clarity	Although operations are individually clear, this is a batch-capable SDK and there are no validation checkpoints or error-recovery feedback loops (e.g. checking poller status, handling partial errors beyond a per-doc is_error skip), and best-practice #4 only passively notes 'results list may contain errors'.	3 / 5
Progressive Disclosure	Content is well-sectioned by operation, but the entire API surface is inlined into SKILL.md with no bundle files and no one-level-deep references for the larger reference material (Available Operations, Client Types, Healthcare/batch details), so structure is present but bulk that could be separate remains inline.	3 / 5
	Total	16 / 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 clearly enumerates concrete SDK capabilities, giving it strong specificity and distinctiveness, but the 'Use for...' clause is too generic to provide explicit trigger guidance. Adding concrete 'Use when...' trigger phrases would raise completeness and trigger_term_quality.

Suggestions

Replace the generic 'Use for natural language processing on text.' with explicit trigger phrasing, e.g. 'Use when the user needs sentiment analysis, entity or PII recognition, key phrase extraction, or language detection on text via the Azure AI Language service.'

Add natural synonyms and phrasings users would actually say (e.g. 'analyze text', 'detect language', 'redact PII', 'extract key phrases') to improve trigger term quality.

Consider noting the Azure Language Service dependency so the trigger is unambiguously tied to Azure, reducing overlap with other NLP skills.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions (sentiment analysis, entity recognition, key phrases, language detection, PII, healthcare NLP) with only minor gaps in coverage such as linked-entity recognition.	4 / 5
Completeness	Has a clear 'what' (the enumerated SDK capabilities) but the 'when' is only a generic 'Use for natural language processing on text' without concrete trigger phrases, which caps completeness at 3 per the missing-explicit-trigger guideline.	3 / 5
Trigger Term Quality	Includes relevant terms like 'sentiment analysis', 'PII', 'NLP', and 'natural language processing', but misses common natural phrasings and synonyms users would say (e.g. 'language detection' vs 'detect language', 'text analytics', 'analyze text').	3 / 5
Distinctiveness Conflict Risk	The SDK-specific naming and enumerated capabilities make it mostly distinct from generic skills, with only minor overlap risk against other Azure AI / NLP library skills.	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-textanalytics-py/SKILL.md
Commit: 57c135b

Reviewed: 5 days 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.