azure-ai-contentsafety-ts

Analyze text and images for harmful content with customizable blocklists.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, lean SDK reference: executable code throughout, consistent error handling, and useful tables. Its weaknesses are structural rather than instructional — a disconnected blocklist lifecycle and a monolithic single-file layout that could benefit from progressive disclosure.

Suggestions

Add an explicit sequenced walkthrough for the blocklist lifecycle (create → add items → analyze with blocklist → optionally delete) with validation checkpoints between steps to improve workflow clarity.

Consider moving the endpoints table, key-types reference, and the full `moderateContent` helper into a separate REFERENCE.md linked from a concise overview, improving progressive disclosure for this 300-line skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-forward with minimal prose, never explaining concepts Claude already knows; nearly every token is executable code, a table, or a directly useful helper.	3 / 3
Actionability	It provides complete, copy-paste-ready TypeScript with imports and consistent `isUnexpected` error handling across analyze, image, and blocklist operations — fully executable, not pseudocode.	3 / 3
Workflow Clarity	Operations are presented as parallel reference sections rather than a sequenced workflow, and the multi-step blocklist lifecycle (create → add items → analyze with → delete) has no explicit validation checkpoints tying the steps together.	2 / 3
Progressive Disclosure	Sections are well-organized, but ~300 lines of API reference, type imports, and a full helper function live inline in a single file with no external references or split content, matching the score-2 "content that should be separate is inline" anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 enough to identify a clear niche but stops short of the score-3 bar by omitting multiple concrete actions, broader trigger-term coverage, and an explicit "Use when..." clause. It is third-person and free of fluff, but reads as a capability statement rather than a trigger-rich invocation hint.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when moderating user-generated content, filtering profanity, or checking images against safety policies") to raise completeness and supply natural trigger terms.

Broaden trigger-term coverage with common user phrasings such as "content moderation", "content safety", "profanity/toxic content detection", and "blocklist filtering".

Expand the action list beyond "analyze" to name concrete operations (classify severity, manage custom blocklists, moderate images) for greater specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ("text and images for harmful content") and one main action ("Analyze") plus a feature ("customizable blocklists"), but it does not list multiple distinct concrete actions like the score-3 anchor's "extract... fill... merge".	2 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"harmful content" and "blocklists" are relevant keywords a user might say, but common variations such as "content moderation", "content safety", "profanity filter", or "toxic content" are missing.	2 / 3
Distinctiveness Conflict Risk	"Analyze text and images for harmful content with customizable blocklists" carves a clear niche (content safety/moderation) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 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: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 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.