azure-ai-contentsafety-ts

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual conten...

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-contentsafety-ts

What are skills?

Review — 89%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Comment Moderation Service

Text content analysis with correct SDK usage

Criteria

Without context

With context

Correct package import

100%

Client as function

100%

isUnexpected import and usage

100%

Environment variable endpoint

100%

AzureKeyCredential usage

100%

Correct analyze path

100%

Harm categories specified

100%

outputType set

100%

categoriesAnalysis used

100%

Severity-based decision

100%

Audit log output

100%

Without context: $0.6026 · 6m 46s · 28 turns · 33 in / 9,273 out tokens

With context: $0.6087 · 5m 15s · 28 turns · 299 in / 7,134 out tokens

100%

Player Chat Moderation with Custom Prohibited Terms

Blocklist management and blocklist-augmented analysis

Criteria

Without context

With context

Correct client package

100%

Client as function

100%

isUnexpected on every call

100%

Blocklist creation uses PATCH

100%

merge-patch content type

100%

Correct create path

100%

Add items endpoint

100%

blocklistNames in analyze

100%

haltOnBlocklistHit present

100%

blocklistsMatch inspection

100%

List blocklists call

100%

Without context: $0.2484 · 3m 21s · 17 turns · 21 in / 4,260 out tokens

With context: $0.4414 · 4m 3s · 22 turns · 440 in / 5,420 out tokens

100%

72%

Media Upload Safety Screening

Image content analysis with base64 and URL inputs

Criteria

Without context

With context

Correct package import

100%

Client as function

100%

isUnexpected on image call

100%

Correct image analyze path

100%

base64 local image

50%

100%

blobUrl remote image

100%

Named types imported

100%

categoriesAnalysis read

100%

Edge case: unreadable file

100%

Edge case: unsupported format

83%

100%

Without context: $0.7605 · 7m 44s · 37 turns · 42 in / 11,337 out tokens

With context: $0.6977 · 5m 43s · 28 turns · 456 in / 10,487 out tokens

Evaluated: about 8 hours ago
Agent: Claude Code

Table of Contents

Comment Moderation Service Player Chat Moderation with Custom Prohibited Terms Media Upload Safety Screening

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.