How do I install the Content Guard skill?

Run npx skillmds@latest add glincker/content-guard in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Content Guard skill do?

Proactive content moderation guard for all incoming messages It is listed under Coding & Dev Tools on SkillMD.

Is Content Guard safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Content Guard?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Content Guard free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Content Guard?

glincker (@glincker) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Content Guard by glincker — Agent Skill

Name: Content Guard
Rating: 4.666666666666667 (3 reviews)
Author: glincker

File contents

Content Guard Skill

This skill provides proactive content moderation across all messaging platforms (WhatsApp, Telegram, Discord, Slack, iMessage, etc.).

Automatic Moderation Mode

When enabled, automatically:

Check all incoming messages for profanity
Flag or censor based on configuration
Log incidents for review

Configuration

The guard can be configured for different strictness levels:

Strict Mode

Block all profanity immediately
No context consideration
Best for: Children's platforms, professional environments

Moderate Mode (Default)

Check with context awareness
Allow profanity in gaming/casual contexts
Best for: General community platforms

Lenient Mode

Only flag severe profanity
Allow most casual language
Best for: Adult communities

Usage in Conversations

When a message comes in:

Run check_profanity on the content
If flagged, use analyze_profanity_context for context
If still flagged after context, censor or warn

Integration

This skill integrates with:

WhatsApp groups (via OpenClaw/Moltbot bridge)
Telegram channels
Discord servers
Slack workspaces
iMessage threads
Matrix rooms
Microsoft Teams

Supported Languages

All 24 languages are supported for moderation: arabic, chinese, czech, danish, dutch, english, esperanto, finnish, french, german, hindi, hungarian, italian, japanese, korean, norwegian, persian, polish, portuguese, russian, spanish, swedish, thai, turkish

Credits

Compatible with OpenClaw, Moltbot (legacy), and Clawdbot (legacy).

Frequently asked questions

Content Guard