azure-ai-contentsafety-ts

Analyze text and images for harmful content with customizable blocklists.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

Quality

Content

72%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 complete, executable TypeScript examples across the main features, but it is a monolithic single-file reference with no progressive disclosure to separate files and no validation checkpoints around the destructive/batch blocklist operations.

Suggestions

Add explicit validation/verification steps around destructive and batch operations (e.g., verify a blocklist exists before deleting, confirm items were added by listing them) to lift workflow clarity above 3.

Move the bulk reference material (API Endpoints table, Key Types imports, Harm Categories) into a separate reference file and link to it from SKILL.md to improve progressive disclosure.

Replace the vacuous 'When to Use' sentence with concrete trigger guidance or remove it to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-first, assuming Claude's competence with minimal prose; only minor stretches could be trimmed, notably the generic closing line 'This skill is applicable to execute the workflow or actions described in the overview.' which adds no information.	4 / 5
Actionability	Provides fully executable, copy-paste-ready TypeScript for the common cases — auth (key + DefaultAzureCredential), text analysis, image analysis (base64 + blob URL), and full blocklist CRUD — with real API paths and the isUnexpected() guard, matching the 'fully executable, covers common cases' anchor.	5 / 5
Workflow Clarity	Operations are organized by feature but presented as standalone snippets rather than a sequenced workflow, and the destructive delete + batch add-items operations have no validation/verification checkpoints, so workflow clarity is capped at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the ~300-line SKILL.md inlines reference material (API endpoints table, key types, harm categories) that could live in separate files; section headers give decent structure, but with no external references it sits at the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

57%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 concise and names the domain plus core actions, but it lacks any explicit 'when to use' trigger guidance and omits common synonyms (e.g., 'content moderation', 'content safety'), capping completeness and distinctiveness at the midpoint.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g., 'Use when analyzing text or images for harmful content, building content moderation, or managing custom blocklists in Azure Content Safety.'

Include common synonyms users actually say — 'content moderation', 'content safety', 'toxicity', 'profanity filter' — to improve trigger term coverage.

Mention 'Azure' or the SDK name to sharpen distinctiveness and reduce overlap with generic moderation skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('text and images for harmful content') plus two concrete actions (analyze, customizable blocklists), matching the 'names domain and 1-2 concrete actions' anchor; it does not enumerate the full range of operations (image analysis modes, blocklist CRUD) needed for a 4.	3 / 5
Completeness	It clearly states what the skill does ('Analyze text and images for harmful content with customizable blocklists') but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes several natural terms a user would say — 'analyze text and images', 'harmful content', 'blocklists' — giving good keyword coverage; a few common synonyms like 'content moderation', 'content safety', or 'toxicity' are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The phrase is somewhat specific to content moderation, but without a provider qualifier ('Azure') or more distinctive triggers it could overlap with other moderation/safety skills, fitting the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	13 / 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/skills/azure-ai-contentsafety-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.