azure-ai-contentsafety-py

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

1.07x

Quality

66%

Does it follow best practices?

Impact

100%

1.07x

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-contentsafety-py/SKILL.md

Quality

Content

70%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, copy-paste-ready code across the main use cases, but it is organized as a flat reference catalog rather than a sequenced workflow, lacks validation/error-handling feedback loops for batch moderation, and inlines material that progressive disclosure would split into referenced files.

Suggestions

Add validation/error-handling feedback (e.g., try/except around analyze_text, check response.action_results or error codes, retry on rate-limit) given the batch moderation use case.

Move the lengthy Harm Categories, Severity Scale, and full API snippets into one-level-deep reference files (e.g., CATEGORIES.md, REFERENCE.md) with clear links from the overview.

Provide a short sequenced "workflow" (configure env -> authenticate -> analyze -> inspect severity -> act on threshold/blocklist hit) so the steps form a coherent process rather than isolated recipes.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable snippets with minimal concept explanation, though the Best Practices list and duplicate Harm/Severity tables add some tokens that could be tightened.	4 / 5
Actionability	Every section provides complete, copy-paste-ready code covering the common cases (API-key and Entra auth, text and image analysis, blocklist CRUD, 8-severity mode) with concrete imports and calls.	5 / 5
Workflow Clarity	Sections are organized by capability rather than sequenced as a workflow, and there are no validation checkpoints or error-handling/feedback loops despite the skill involving batch moderation operations, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files and no one-level-deep references to split out the lengthy API reference and tables; structure exists via headers but content that could live in separate files is inlined.	3 / 5
	Total	15 / 20 Passed

Description

62%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 is specific and third-person with a clear capability statement, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and leaves trigger-term coverage only partial.

Suggestions

Add an explicit trigger clause, e.g. "Use when moderating user- or AI-generated text and images for hate, sexual, violence, or self-harm content."

Include natural synonyms users say, such as "content moderation," "safety filtering," and "toxicity/profanity detection," alongside the existing terms.

Mention additional concrete capabilities (blocklist management, configurable severity thresholds) to broaden specificity.

Dimension	Reasoning	Score
Specificity	It names the domain (Azure AI Content Safety SDK) and concrete actions ("detecting harmful content in text and images" with "multi-severity classification"), but stops short of listing several specific actions like blocklist management or severity thresholds, leaving minor coverage gaps.	4 / 5
Completeness	The "what" is clear (detect harmful content in text and images with multi-severity classification), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It surfaces natural terms like "harmful content," "text and images," and "multi-severity classification," but omits common variations users would say (e.g., content moderation, safety filtering, profanity/toxicity detection) and has no file-extension or synonym coverage.	3 / 5
Distinctiveness Conflict Risk	The Azure AI Content Safety SDK plus text/image harmful-content detection carve out a fairly distinct niche with minimal overlap risk against generic skills, though it could still brush against broader content-moderation tooling.	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-contentsafety-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.