content-moderation-api git:20260507.44b06c0A

Immutable. This exact content is served forever at /api/v1/blob/65b46a0bea27c8d8.

---
name: content-moderation-api
description: Content moderation API integration using OpenAI Moderation, Perspective API, and others
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
graph:
  domains: [domain:software-engineering]
  specializations: [specialization:ai-agents-conversational]
  skillAreas: [skill-area:natural-language-processing, skill-area:safety-redteaming]
  roles: [role:ml-engineer, role:backend-engineer]
  workflows: [workflow:feature-development, workflow:ml-model-lifecycle]

---

# Content Moderation API Skill

## Capabilities

- Integrate OpenAI Moderation API
- Set up Perspective API for toxicity detection
- Configure moderation thresholds
- Implement content filtering pipelines
- Design moderation response handling
- Create moderation logging and reporting

## Target Processes

- content-moderation-safety
- system-prompt-guardrails

## Implementation Details

### Moderation APIs

1. **OpenAI Moderation**: Hate, violence, self-harm, sexual content
2. **Perspective API**: Toxicity, insult, profanity, threat
3. **Azure Content Safety**: Text and image moderation
4. **LlamaGuard**: Open-source safety classifier

### Configuration Options

- API credentials and endpoints
- Category thresholds
- Action policies (block, warn, flag)
- Logging configuration
- Fallback behavior

### Best Practices

- Set appropriate thresholds
- Handle edge cases gracefully
- Log moderation decisions
- Regular threshold review
- Multi-layer moderation

### Dependencies

- openai
- google-cloud-language (Perspective)
- azure-ai-contentsafety