Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Wardrobe Builder v1

    2

    Turn your photos and shopping order screenshots into a structured, searchable JSON wardrobe database with AI vision and automated linting.

    Free

    3 usesSecurity scanned

    wardrobe-builder-v1

    Example session with this skill installed

    See the media section on this page for what you can upload to the agent while using this skill. This field does not support pictures.

    • Read your context and instructions
    • Compiled the wardrobe-builder-v1

    Done — added this item to your wardrobe via wardrobe-builder v1.
    New wardrobe item
    ID: RalphLaurenwhitegraphicprintregularT-shirt
    Category: tops
    Brand: Ralph Lauren
    Type: T-shirt
    Photo: items/tops/RalphLaurenwhitegraphicprintregularT-shirt.jpg
    Description: White Ralph Lauren Polo Bear crew-neck short-sleeve T-shirt with front bear graphic and Polo Bear text.

    Verified
    Item was written to wardrobe.json
    Photo file exists in the wardrobe item folder
    Wardrobe now has 1 item
    Lint check: no missing required fields or image issues.

    Item was written to wardrobe.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    wardrobe-builder is a developer-centric asset management system for personal fashion. It transforms messy closet photos, shopping screenshots, and multi-item montages into a clean, structured JSON database. It handles the heavy lifting of OCR brand detection, visual feature extraction (color, fit, material), and automated image processing like background removal or intelligent cropping.

    How it works

    This skill provides a robust pipeline consisting of a directory scaffolder, an ingestion engine, a safe-write layer, and a linter. It can detect garment boundaries, split composite images into individual items, and map them to a strict schema. To ensure data integrity, it uses a confidence-based review queue—questionable data is flagged for your approval rather than polluting your database.

    Supported Tools

    • Python-based automation for local file management
    • OCR & Computer Vision for attribute tagging
    • Lark/Feishu CLI integration for remote photo uploading
    • JSON-based local storage (no cloud lock-in)

    Why use this skill

    Manually tagging a 200-item wardrobe is tedious. Prompting an AI to "remember my clothes" results in hallucinations and lost context. This skill provides a permanent, local "source of truth" that other agents (like stylists) can query reliably. It includes a built-in linter to fix broken image paths and schema violations, keeping your data production-ready.

    ,example_output:

    The better LLM's vision capability is, the better the result. Require multi-modal LLM.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    3 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed5 months ago

    What's inside

    Frequently Asked Questions

    It uses AI vision and OCR to extract attributes like brand, material, and color from photos or screenshots, then organizes them into a structured JSON database, eliminating manual data entry.

    The skill includes a built-in linter that flags questionable data for review and a local JSON storage system, ensuring your data remains accurate and accessible without cloud lock-in.

    Yes, it is designed to handle complex inputs, including multi-item montages and shopping screenshots, by detecting garment boundaries and splitting them into individual items.

    The skill provides a standard JSON source of truth, making it highly compatible with AI stylists, outfit generators, or any agent that can query structured data files.

    You receive the full pipeline including the directory scaffolder, ingestion engine, safe-write layer, and the linter, along with Python-based automation scripts for local management.

    New in Data & Databases