skills.rest
DTMC-marketplace
DTMC-marketplaceOFFICIAL
Explore all skills by this author →
GitHub

hate-speech-detector

Classify text for hate speech and offensive language using the HateSonar API.

2|Updated Jan 15, 2026
Search Tags:#compliance#bias detection#content moderation#eu ai act#societal risk#hate speech
One-click install
npx skills add https://github.com/DTMC-marketplace/governance --skill hate-speech-detector
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hate-speech-detector
Source: https://github.com/DTMC-marketplace/governance/tree/main/skills/hate-speech-detector
Command: npx skills add https://github.com/DTMC-marketplace/governance --skill hate-speech-detector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps identify and flag hate speech and discriminatory language in text, crucial for maintaining safe online environments and ensuring AI compliance.

Core Features & Use Cases

  • Hate Speech Detection: Utilizes the HateSonar API to classify text.
  • Compliance Assessment: Aids in evaluating AI systems against societal risk requirements like the EU AI Act's Art. 9.
  • Risk Mitigation: Provides a tool to implement controls for societal risks.
  • Use Case: A content moderation team can use this skill to automatically scan user-generated comments for hate speech, flagging them for review.

Quick Start

Use the hate-speech-detector skill to analyze the provided text for hate speech.

Frequently Asked Questions about hate-speech-detector

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect hate speech in user-generated comments?▼

To detect hate speech in user-generated comments, the skill analyzes text using the HateSonar API and classifies content with confidence scores for hate speech, offensive language, or neutral material.

How does bias detection work for EU AI Act compliance?▼

Bias detection for EU AI Act compliance works by evaluating text for discriminatory language and assessing societal risks against Article 9 requirements, providing confidence scores to support risk mitigation controls.

Can I use this for automated content moderation of offensive language?▼

Yes, you can use this for automated content moderation of offensive language by scanning user-generated text, categorizing it as hate speech, offensive, or neutral, and flagging problematic comments for review.

What is the difference between offensive language and hate speech classification?▼

The difference between offensive language and hate speech classification is determined by the HateSonar API, which assigns separate confidence scores to distinguish general offensive content from targeted discriminatory language.

Do I need to configure external components to assess societal risks?▼

No, you do not need to configure external components to assess societal risks, as the skill operates independently without dependencies to evaluate text and map findings to EU AI Act Article 9 requirements.

Related Skills

Explore More Legal & Compliance Skills→
brainbrewlabsbrainbrewlabs
7

content-scanning

Scans user-generated content for policy violations and outputs structured recommendations.

Official
Intermediate
DTMC-marketplaceDTMC-marketplace

moderate-content-api

Moderate content and assess compliance with EU AI Act Art. 9.

Official
Intermediate
jcoutsousajcoutsousa

data-governance-audit

Audit AI training datasets for EU AI Act compliance and governance.

Community
Advanced
DTMC-marketplaceDTMC-marketplace

toxicity-detection

Detect and filter toxic content in AI inputs and outputs.

Official
Intermediate