Automate content filtering and safety checks for NodeJS applications.
npx skills add https://github.com/CleanExpo/DR-NRPG --skill content-moderation
Please help me install this Agent Skill. Skill: Content Moderation Source: https://github.com/CleanExpo/DR-NRPG/tree/main/.skills/custom/content-moderation Command: npx skills add https://github.com/CleanExpo/DR-NRPG --skill content-moderation
This Skill automates the process of filtering user-generated and AI-generated content to ensure it is safe, appropriate, and adheres to defined policies, preventing harmful or inappropriate material from being displayed or processed.
Apply content moderation to user input using the content-moderation skill.
High-intent search queries and answers about installing and using this skill.
Automate content moderation for NodeJS by applying rule-based pattern matching and AI-powered toxicity detection through middleware to scan comments for hate speech, PII, or spam before publication.
AI toxicity detection works with rule-based filtering by applying pattern matching to catch known violations and AI models to identify contextual toxicity, ensuring comprehensive content safety and compliance.
You can use middleware to enforce content policies automatically, applying rule-based and AI-powered checks to block harmful text or route flagged items to a queue for human review.
A human review queue is included to handle flagged items, allowing moderators to evaluate edge cases caught by rule-based and AI-powered safety checks before final decisions are logged for auditability.
Content moderation logging supports compliance audits by recording all moderation decisions made during automated PII and spam filtering, providing a verifiable trail of actions taken on flagged content.
The best way to integrate content moderation is by connecting the automated filtering checks directly with your existing AI provider layers, enabling seamless toxicity detection and policy enforcement.
ApiliumCodeDetect and classify prompt injection patterns in text data with risk levels.
brainbrewlabsCompile contextual evidence and policy-aligned decision options for flagged content review.
skywatch-bskyQuery Osprey rule execution results and sidecar metrics in ClickHouse.
FOUNDUPSDetect and block spam, toxic content, and rate-limit violations in YouTube live chat.
