AI Agent Hub
Back to skills
Social Media Sensitive Text Check icon

Social Media Sensitive Text Check

Content Creation Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Please install @user_825d9e7e/socialdatax-sensitive-check by following the guide at https://skillhub.cn/install/skillhub.md.

About this skill

Problem

Social posts often get rejected, throttled, or reported because of sensitive terms, banned words, or platform-specific risky phrasing. Manual review depends on personal experience and ad hoc word lists, making it hard to cover context differences across Xiaohongshu, Douyin, and Kuaishou.

How It Works

This skill sends a draft to SocialDataX's sensitive-text detection service. The main outputs are whether the text violates rules, risk level, matched risk types, highlighted risky fragments, and rewrite suggestions. The usual flow is: paste the copy, optionally set generic, xhs, douyin, or kuaishou, then read the structured result. It fits pre-publish checks, content safety review, go/no-go decisions, and turning risky phrasing into safer wording.

Boundaries and Notes

The current v1 supports text-only sensitive detection, not image content; results depend on server-side dictionaries, platform rules, and risk models, so they should not replace final human review. Calls use SOCIALDATAX_API_KEY, but the skill file itself does not include the key and will not read local browser data, log in, post, like, or comment. If a balance error occurs, follow the returned recharge instruction instead of repeatedly retrying or replacing API results with web search.

Use Cases

  • A Xiaohongshu operations editor checks a seed post before publishing to identify banned terms, risk fragments, and safer rewrite suggestions.
  • A Douyin script editor reviews a voiceover draft before submission to replace high-risk phrasing that may trigger throttling or review blocks.
  • A Kuaishou merchant checks campaign copy for promotional claims before release to confirm compliance and obtain safer wording for the listing page.
  • A content safety manager reviews batch user submissions, extracts risky fragments, and prepares disposition notes for the moderator queue for review.

Best For

  • Xiaohongshu or Douyin operations editor: checks seed posts before publishing for banned terms and safer rewrites
  • Voiceover script editor: reviews drafts before submission to replace high-risk phrasing that may cause throttling
  • Merchant operations lead: checks promotional copy before release to confirm whether it can be published
  • Content safety reviewer: scans batch submissions, flags risky fragments, and compiles handling suggestions