Skills
.Work. You
Rest

ai-moderating-content

Community

Auto-moderate user content with DSPy

Content & Communication#routing#content#moderation#classification#policy#harassment#nsfw
Authorlebsral
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Auto-moderate user-generated content by detecting policy violations, scoring severity, and routing decisions to automated actions or human review.

Core Features & Use Cases

  • Classification + severity scoring: Identify policy violations (spam, hate, NSFW, harassment) and assign a severity level.
  • Confidence-based routing: Route decisions to approve, warn, human_review, or remove based on confidence and severity.
  • Policy enforcement with asserts: Use hard blocks to intercept obvious issues before LM evaluation and ensure auditable decisions.
  • Use Case: Moderate comments in forums, product reviews, marketplace listings, and social posts to keep communities safe.

Quick Start

Create a DSPy-based moderation module that classifies content, assigns severity, and routes decisions (approve, warn, human_review, or remove) according to platform policies.

Dependency Matrix

Required Modules

None required

Components

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: ai-moderating-content
Download link: https://github.com/lebsral/DSPy-Programming-not-prompting-LMs-skills/archive/main.zip#ai-moderating-content

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.