A sophisticated routing engine that transforms natural language descriptions into structured visual configurations for automated image generation.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install phy-content-type-router
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install phy-content-type-router using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Content Type Router is a powerful classification system designed to bridge the gap between abstract text descriptions and concrete visual layout rules. By analyzing user intent and industry context, it maps requests to one of 17 predefined content types, such as hero shots, infographics, or lifestyle photography. This Openclaw Skills component ensures that downstream image generation models receive precise instructions regarding focal points, subject coverage, and typography constraints.
Built for developers and creative technologists, this skill provides a robust Python-based API to automate the selection of visual modes—ranging from pure photography to text-heavy call-to-action graphics. By integrating this into your creative workflow, you can maintain brand consistency and technical accuracy across diverse visual assets without manual intervention, leveraging the power of Openclaw Skills to streamline production.
To get started with this component of Openclaw Skills, install the package and configure your environment:
# Install the content type router package
pip install content-type-router
# Optional: Enable database-backed content types for brand-specific overrides
export USE_DB_CONTENT_TYPES=true
Initialize the detection in your Python script:
from content_types.registry import detect_content_type
# Detect the best fit for your content
slug, confidence = detect_content_type(
description="A top-down flat lay of coffee and a laptop",
industry="food"
)
The skill organizes its output into a highly structured metadata taxonomy designed for programmatic consumption. It uses two primary data structures to define visual intent:
| Structure | Key Attributes |
|---|---|
| ContentTypeConfig | slug, visual_mode, generation_hints, negative_prompts, aspect_ratios |
| LayoutRules | focal_point, text_zone, subject_coverage_min/max, camera_angle, background |
Each content type is mapped to a Visual Mode: pure_visual (no text), educational (limited labels), or cta (text required), which dictates how the Openclaw Skills router handles typographic overlays.
Loading
An advanced brand identity extraction engine that uses computer vision and web scraping to generate structured visual profiles from any website.

A specialized weather data integration for fetching forecasts, historical trends, and site-specific risk assessments for construction project management.

A privacy-first metasearch skill that enables AI agents to query local SearXNG instances for web, image, and news data.

Perform real-time web searches directly within your AI agent's workflow to access the latest internet data.

A powerful tool for tracking and analyzing high-performing Twitter creators to extract viral content patterns and growth insights within Openclaw Skills.

A structured 15-20 minute engagement routine designed to help indie developers and founders build a consistent social presence across multiple platforms.








































