CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A highly actionable SDK reference with executable, error-checked examples for every operation. Its weaknesses are inlined detail that belongs in reference files (no progressive disclosure) and a few filler sections, plus missing guidance for the long-running poller operations.

Suggestions

Move the Healthcare Text Analytics, Multiple Analysis (Batch), and Async Client sections into a references/ file (e.g., references/advanced.md) and link them from a short 'Advanced' section, keeping SKILL.md to setup, auth, and the core synchronous operations.

Delete the 'When to Use' filler section and the opening line that restates the frontmatter description; the body adds no value there.

Add brief poller guidance for the long-running operations (e.g., checking poller.status(), handling partial results, and the 10-document batch limit) to close the workflow-validation gaps.

DimensionReasoningScore

Conciseness

The body is mostly lean code examples and tables with no concept explanations Claude already knows, but contains trimmable filler such as the intro line duplicating the description and the vacuous 'When to Use: This skill is applicable to execute the workflow or actions described in the overview.' section.

4 / 5

Actionability

Every section is fully executable and copy-paste ready: pip install with pinned version, environment variables, both auth flows, and complete result-handling code covering all eight listed operations, matching the anchor for executable guidance with common cases covered.

5 / 5

Workflow Clarity

Each operation is a clear, unambiguous recipe with explicit per-document error checkpoints ('if not doc.is_error'), but guidance for the long-running pollers (begin_analyze_healthcare_entities, begin_analyze_actions) lacks status/retry/timeout handling, leaving minor validation gaps.

4 / 5

Progressive Disclosure

Headers and tables give the ~220-line body reasonable navigation, but all eight per-operation examples are inlined with no reference files at all — the healthcare, batch-actions, and async sections could be split into one-level-deep references, matching the anchor where content that should be separate is inline.

3 / 5

Total

16

/

20

Passed

Description

80%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.

A strong description that concretely enumerates the SDK's capabilities and includes an explicit use clause. The trigger section is somewhat generic ('natural language processing on text') and misses a few natural synonym terms.

DimensionReasoningScore

Specificity

The description enumerates six concrete capabilities — 'sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP' — which is comprehensive coverage of the SDK's operations, matching the multiple-specific-actions anchor rather than the 'minor gaps' anchor below it.

5 / 5

Completeness

Both what ('Azure AI Text Analytics SDK for sentiment analysis, entity recognition...') and when ('Use for natural language processing on text') are present, but the when-clause is generic and could name concrete trigger scenarios more explicitly.

4 / 5

Trigger Term Quality

Natural phrases like 'sentiment analysis', 'entity recognition', 'key phrases', 'language detection', and 'natural language processing' cover what users would say, but common variations such as 'NER', 'PII redaction', or 'text mining' are absent.

4 / 5

Distinctiveness Conflict Risk

The Azure AI Text Analytics SDK niche is clear and unlikely to trigger for unrelated skills, with only minor overlap risk against other general NLP library skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

skills/azure-ai-textanalytics-py/SKILL.md

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.