azure-ai-contentsafety-ts

Analyze text and images for harmful content with customizable blocklists.

Quality

63%

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 ./skills/antigravity-azure-ai-contentsafety-ts/SKILL.md

The canonical home for this skill is azure-ai-contentsafety-ts in sickn33/antigravity-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 body is highly actionable with executable code and well-organized reference tables, but it lacks validation checkpoints for destructive blocklist operations and keeps all reference material inline rather than splitting it into separate files.

Suggestions

Add an explicit validation step before destructive operations (e.g. confirm the blocklist exists and review its items before calling delete).

Move the API Endpoints table and Key Types reference into a separate REFERENCE.md and link to it from SKILL.md to improve progressive disclosure.

Replace the generic 'When to Use' / 'Limitations' boilerplate with skill-specific guidance or remove it to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, directly usable code blocks and reference tables with little concept explanation Claude already knows; only minor filler (the generic 'When to Use' and 'Limitations' boilerplate) could be trimmed, matching the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	Copy-paste-ready TypeScript covers analyze text, image (base64 and blob URL), full blocklist CRUD, and a complete moderateContent helper, matching the 'fully executable, covers common cases' anchor.	5 / 5
Workflow Clarity	Operations are sequenced via section order and the API Endpoints table, but destructive/batch operations (Delete Blocklist, Add Blocklist Items) have no validation checkpoints, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Section headers and tables give good structure, but with no bundle files present everything (~300 lines, including the API Endpoints reference and Key Types) is inlined in SKILL.md, matching the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

53%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 states a clear purpose and niche but omits any explicit 'when to use' trigger guidance, which caps its completeness, and lacks natural synonyms that would improve trigger term quality.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when moderating user-generated text or images, filtering toxic/profane content, or applying custom blocklists.'

Include natural synonyms users say ('content moderation', 'toxic content', 'profanity', 'safety review') to broaden trigger coverage.

List a couple more concrete actions (e.g. 'score severity across Hate/Sexual/Violence/SelfHarm categories') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Analyze text and images for harmful content' and 'customizable blocklists' name the domain plus two concrete actions, but coverage is not comprehensive (no mention of severity scoring, thresholds, or image analysis variants), matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	The 'what' is clear ('Analyze text and images for harmful content with customizable blocklists') but there is no 'Use when...' trigger clause, so per the rubric guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	'harmful content', 'blocklists', and 'text and images' are relevant keywords, but common natural synonyms users say such as 'content moderation', 'toxic content', 'profanity filter', or 'safety' are missing, fitting the anchor for some relevant keywords lacking variations.	3 / 5
Distinctiveness Conflict Risk	The phrase targets a clear niche (content safety moderation with blocklists) that is mostly distinct from other skills, with only minor overlap risk against general moderation skills, matching the 'mostly distinct' anchor.	4 / 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: boisenoise/skills-collections
Path: skills/antigravity-azure-ai-contentsafety-ts/SKILL.md
Commit: 19c310e

Reviewed: about 17 hours 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.