NSFW Detection Skills for Openclaw

A comprehensive suite of safety tools for detecting and filtering explicit content using Openclaw Skills.

raghulpasupathi
v1.0.0
Feb 22, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install nsfw-detection

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install nsfw-detection using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is NSFW Detection Skills?

NSFW Detection Skills provides a robust suite of tools designed to maintain digital safety by identifying inappropriate or adult content. This collection of Openclaw Skills leverages local ONNX models for high-performance image classification and a domain reputation database to prevent access to harmful sites without compromising privacy.

By integrating these tools, developers can build safer environments for users, protecting children and sensitive workflows from explicit content through context-aware filtering. The system is designed to run locally, ensuring that sensitive data never leaves the host environment while maintaining a high degree of accuracy across various categories of explicit imagery.

NSFW Detection Skills Use Cases

  • Automated blocking of pornographic and explicit imagery in web applications.
  • Domain-level pre-filtering to prevent access to known adult websites.
  • Protecting children and minors from harmful online content with strict safety tiers.
  • AI-assisted content moderation for community platforms and forums.
  • Implementing tiered safety levels (Strict, Balanced, Lenient) based on specific user age groups.

How NSFW Detection Skills Works

  1. The system initiates a domain reputation check to quickly identify and block known adult URLs before visual analysis.
  2. If a URL passes, the image detection skill retrieves visual content for processing via the local ONNX model.
  3. The model performs multi-category classification, scoring content for porn, hentai, or suggestive themes.
  4. Context-aware logic applies exceptions for medical or artistic content based on configured settings.
  5. The skill returns a confidence score and recommended action to the host application to finalize the moderation workflow.

NSFW Detection Skills Setup

Via npm

Install the specific packages required for visual detection and reputation checking:

npm install @clawhub/nsfw-detector
npm install @clawhub/url-reputation

Via ClawHub

You can also integrate the full detection suite directly via the Openclaw Skills repository:

https://clawhub.ai/raghulpasupathi/nsfw-detection

NSFW Detection Skills Data Schema & Taxonomy

Property Type Description
isNSFW Boolean Indicates if the content exceeds the safety threshold.
confidence Float The probability score of the detection (0.0 to 1.0).
categories Object Detailed breakdown for porn, sexy, hentai, and drawings.
action String Recommended handling instruction (e.g., 'block', 'warn').
contextAware Boolean Whether the system accounted for medical or artistic exceptions.

NSFW Detection Skills Advanced Features

  • Multi-category classification including drawings, hentai, and explicit photography.
  • Skin tone detection algorithms to enhance visual analysis accuracy.
  • Local ONNX model execution ensures no external API calls and zero data leakage.
  • Flexible configuration profiles for Child, Teen, and Adult safety levels.
  • High-performance domain caching for the URL reputation checker to speed up repetitive lookups.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*