moderation

Audit social media content for policy violations and generate risk reports.

12|3|Updated Jun 17, 2026
One-click install
npx skills add https://github.com/phuhao00/bony-agent --skill moderation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: moderation
Source: https://github.com/phuhao00/bony-agent/tree/main/.agent/skills/moderation
Command: npx skills add https://github.com/phuhao00/bony-agent --skill moderation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires langchain, langchain-openai, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the challenge of maintaining content compliance across multiple social media platforms, preventing account penalties and brand damage caused by accidental policy violations.

Core Features & Use Cases

  • Multi-Platform Compliance: Automatically checks content against specific rules for Douyin, Xiaohongshu, Bilibili, and WeChat.
  • Risk Assessment: Identifies sensitive words, prohibited advertising language, and potential policy violations with actionable feedback.
  • Automated Remediation: Provides safe, compliant alternatives for flagged content to ensure your message remains effective while staying within platform guidelines.

Quick Start

Use the moderation skill to check the following text for compliance issues on the Xiaohongshu platform.

Frequently Asked Questions about moderation

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

FAQPage Schema
How do I check social media content for policy violations on Xiaohongshu and Douyin?

Social media content compliance checking evaluates text against platform-specific rules to identify prohibited advertising language and policy violations on networks like Xiaohongshu and Douyin. It scans for sensitive terminology and generates structured risk reports with remediation suggestions.

What is automated content risk assessment for social media platforms?

Automated content risk assessment detects sensitive words and platform-specific policy violations across social media networks. It audits text for regulatory and platform-level adherence, providing structured reports and safe content alternatives to prevent account penalties.

Can I use langchain to automate content moderation for Bilibili and WeChat?

Yes, you can automate content moderation for Bilibili and WeChat using langchain. The skill integrates langchain and langchain-openai to audit diverse social media platforms, detecting prohibited language and providing automated remediation suggestions.

How do I fix sensitive terminology in social media posts before publishing?

Fixing sensitive terminology in social media posts requires automated content remediation, which identifies flagged words and provides safe, compliant alternatives. This ensures your message remains effective while adhering to platform-specific guidelines and preventing account penalties.

Does automated compliance checking work for multi-platform social media campaigns?

Yes, automated compliance checking works for multi-platform social media campaigns by evaluating content against specific rules for Douyin, Xiaohongshu, Bilibili, and WeChat simultaneously. It detects policy violations and provides actionable feedback to ensure regulatory adherence.