Create a personal Chrome extension that uses an AI vision model and a keyboard shortcut to generate detailed descriptions of images posted in Slack, improving accessibility and efficiency.
with Claire Vo
Begin by creating a new Chrome extension. In the manifest file, define a custom command that listens for a specific keyboard shortcut, such as Ctrl+Shift+D, and scope its activation to the Slack web app.
Write a content script that, when the shortcut is triggered, identifies the image element currently in focus within the Slack message thread and extracts its source URL or data.
Send the captured image data to an AI model with vision capabilities, like the ChatGPT API. The request should ask the model to provide a detailed description of the image's contents.
Once the AI returns the text description, display it in a user-friendly, accessible modal window that appears over the Slack interface, so you can read it without losing context.
Enhance the tool by adding a text input field to the modal. This allows you to ask follow-up questions about the image, sending them back to the AI to get more specific details.
what age child is this for?
Supercharge your engineering velocity by using Claude Opus 4.6 to rapidly build features and then leveraging GPT-5.3 Codex to perform a rigorous, principal-level code review for production hardening.
Leverage Claude Opus 4.6 within Cursor to perform a complete, creative redesign of a marketing website, from initial high-level concepts to a polished, on-brand final product.
Follow a step-by-step process to build a custom Chrome extension that summarizes links in Slack using Claude Code, from voice-dictated PRD to a fully debugged, accessible tool.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.