store-teardown

To extract a color palette and design brief from a Taobao store, this skill automates the collection of store images and analyzes visual elements like color schemes, typography, and photography styles. It outputs a structured YAML or JSON design brief for design teams.

Automating ecommerce store teardown involves using a modular pipeline to collect store visuals from platforms like Tmall, JD, or Pinduoduo. This process extracts layout language and image styles, producing a structured design brief that captures the store's visual DNA.

Yes, you can analyze store visuals from JD and Pinduoduo using Python. The skill uses libraries like beautifulsoup4, requests, and instaloader for image downloading, alongside numpy and scikit-learn for local color extraction and visual data analysis.

Turning scattered store images into a structured design brief is done by processing collected images through local color extraction and optional Gemini AI analysis. This evaluates composition and typography impressions, outputting a cohesive brief for brand teams.

Store visual analysis supports manual image input as an alternative to automated fetching. You can provide your own images to the pipeline, which will then perform color palette extraction and photography style analysis to generate the final design brief.

An automated visual teardown of an ecommerce store includes analysis of color palettes, typography cues, composition, and photography style. This visual data is synthesized into a designer-ready brief formatted in YAML or JSON for immediate integration.