A specialized skill for extracting normalized design inspiration and metadata from Dribbble, Pinterest, and Behance using login-free browser automation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install design-platform-search
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install design-platform-search 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 Public Design Search Skill?
The Public Design Search skill is designed for high-efficiency, login-free extraction of creative assets from major design platforms including Dribbble, Pinterest, and Behance. By focusing on public search pages as the primary source of truth, this tool within the Openclaw Skills ecosystem allows developers and AI agents to gather design references, cover images, and author metadata without the overhead of session management or authentication. It provides a robust framework for retrieving visual inspiration while maintaining a lightweight footprint.
Built to handle the complexities of modern web platforms, the skill utilizes browser automation to navigate search results and extract normalized data fields. It is particularly effective for creative workflows where multi-platform aggregation is required, ensuring that data from diverse sources is returned in a consistent, predictable format. This makes it an essential component for building automated moodboards, trend analysis tools, or design research assistants.
Public Design Search Skill Use Cases
- Automating the collection of visual moodboards based on specific design tags or keywords.
- Aggregating cross-platform search results for competitive design research.
- Programmatically retrieving cover images and project URLs for design inspiration galleries.
- Monitoring design trends across Dribbble, Pinterest, and Behance without manual searching.
- Feeding high-quality visual metadata into AI-driven creative pipelines.
How Public Design Search Skill Works
- The skill identifies the target platforms and selects search tags based on provided input or optimized taxonomies.
- It dynamically constructs search URLs for Dribbble, Pinterest, and Behance using URL-encoded tags.
- Browser automation is triggered to load the search results, bypassing the limitations of raw HTTP requests.
- Candidate cards are identified on the search page, and primary fields like titles and image URLs are extracted immediately.
- If required and budget allows, the skill performs a targeted backfill by visiting detail pages to capture publication dates and missing author names.
- The extracted data is cleaned and mapped into a normalized JSON schema for downstream usage.
Public Design Search Skill Setup
To integrate this skill into your workflow, ensure your Openclaw Skills environment is configured for browser-based extraction. This skill relies on local reference files for tag management and platform-specific logic.
# Navigate to your skills directory
cd skills/design-platform-search
# Ensure your browser automation drivers are updated
# This skill typically leverages Playwright or similar browser engines
Configuration for regional access or proxy usage should be defined in your network guidance settings to handle platforms like Pinterest or Behance in restricted environments.
Public Design Search Skill Data Schema & Taxonomy
The skill produces a consistent output format to ensure interoperability between different AI agents and databases. Below is the primary metadata structure:
| Field | Type | Description |
|---|---|---|
title |
string | The extracted title of the design project or pin. |
platform |
string | The source platform (dribbble, pinterest, or behance). |
source_url |
string | The canonical URL of the original design project. |
cover_image_url |
string | The primary thumbnail or cover image identified on the search page. |
author_name |
string | The creator's name, defaulted to 'Unknown' if not found. |
publish_time |
string/null | ISO formatted timestamp of the project publication. |
keyword |
string | The original search tag used to generate the result. |
matched_tags |
array | A list of relevant tags or categories associated with the result. |
Public Design Search Skill Advanced Features
- Intelligent detail-page backfilling that prioritizes search-page speed while allowing for deep metadata extraction when necessary.
- Multi-platform normalization that converts disparate HTML structures into a single unified JSON schema.
- Built-in network resilience with specific guidance for SOCKS5 and HTTP proxy configurations.
- Tag taxonomy integration to help agents select the most effective search terms across different design ecosystems.
- Login-free architecture ensuring stability and reducing the risk of account-related session expirations.
SKILL.md
Loading
Related Openclaw Skills
PDF Splitter by Keyword
An intelligent PDF processing tool that automatically identifies and extracts pages containing specific keywords, supporting both digital and scanned documents.
UniversalDocProcessor
A sophisticated document processing framework that provides intelligent analysis, modification, and conversion for any file format using Openclaw Skills.
Claude Says Go To Sleep
A specialized AI skill that prioritizes developer well-being by strictly enforcing rest and sleep boundaries.
Warehouse Network Optimizer
A high-performance logistics optimization tool using Mixed-Integer Linear Programming to determine optimal warehouse locations and delivery routes.
Get-Note-Sifter
An intelligent AI assistant that bridges the gap between raw web clippings and structured Obsidian research vaults.
Auto Model Router
An intelligent routing system that automatically assigns the most suitable AI model based on task complexity and domain for OpenClaw agents.
Featured*
