Clean Completely free

Paste a vision model's segmentation output - objects with box_2d bounds and base64 masks - and see the boxes and masks drawn over the image, with a switchable co-ordinate origin for when a mask lands mirrored or rotated. Ships an embedded example so it demos without an upload. Runs fully client-side. Imported Claude artifact. Source: https://github.com/simonw/tools (mask-visualizer.html, Apache-2.0).

Share

Details

PricingCompletely free
Security scanClean — skill and frontend scanned
Created2026-08-25
Updated2026-08-25
View source prompt + release files — fork-enabled apps share their full source

System prompt (SKILL.md)

---
name: mask-visualizer
description: Paste a vision model's segmentation JSON (box_2d + base64 mask) and see the boxes and masks drawn over the image.
metadata:
  tags:
    - artifact-import
    - ai
  source_url: https://tools.simonwillison.net/mask-visualizer
  github_repo_url: https://github.com/simonw/tools
---

# Mask Visualizer

An imported Claude artifact. Paste the JSON a vision model returns - an array
of objects carrying `box_2d` bounds and a base64 `mask` - and it renders the
boxes and masks over the image so you can see what the model actually
segmented, with a per-region information panel.

The co-ordinate origin is switchable between all four corners, which is the
usual reason a mask lands rotated or mirrored when you plot it yourself.
A "Load example" button ships embedded sample data, so the tool demonstrates
itself without an upload.

Decoding and drawing happen in the page. Nothing is uploaded, no model is
called, and nothing is metered.

Release files (files)

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.