toxicity-detection
OfficialDetect toxic content in AI.
AuthorDTMC-marketplace
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill addresses the critical need to identify and mitigate toxic and harmful content generated or processed by AI systems, ensuring safer and more compliant AI interactions.
Core Features & Use Cases
- Toxicity Scoring: Implements multi-model scoring to assess the level of toxicity in text.
- Content Filtering: Provides pipelines to filter out harmful content based on defined thresholds.
- Compliance Assessment: Aids in evaluating AI systems against regulatory requirements like the EU AI Act's Article 9.
- Use Case: Automatically scan user-generated content within a chatbot to flag and remove hate speech before it is displayed to other users.
Quick Start
Use the toxicity-detection skill to assess the input text for harmful content.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: toxicity-detection Download link: https://github.com/DTMC-marketplace/governance/archive/main.zip#toxicity-detection Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.