Skip to content

Latest commit

 

History

History
124 lines (89 loc) · 5.18 KB

CLAUDE.md

File metadata and controls

124 lines (89 loc) · 5.18 KB

PLSFIX-THX - Give Your AI Agent Perfect Context

Stop Typing. Start Showing.

PLSFIX-THX is a Chrome extension that helps solo developers and small teams communicate perfectly with AI agents. Capture your screen, add numbered annotations pointing to exact locations, and share crystal-clear feedback with Claude, ChatGPT, or any AI in seconds.

🚀 Key Features

⚡ Instant Screen Capture

  • One-Click Capture: Use keyboard shortcuts (Alt+Shift+S for area, Alt+Shift+F for full page) or the extension icon
  • No Delays: Start annotating immediately—no uploading, no waiting
  • Capture Anywhere: Works on any website you're viewing

🎯 Numbered Annotations That Point Exactly

  • Precise Markers: Click anywhere to add numbered markers with text notes
  • No Confusion: Your AI sees exactly what you're pointing at
  • Drag & Drop: Reposition annotations to point at the exact location

🤖 Works with Any AI Tool

  • Universal Compatibility: ChatGPT, Claude, Gemini, Cursor, Windsurf—if it accepts images, it works
  • Export to PNG: Annotations are baked into the image
  • Copy and Paste: Share in seconds

🚀 Built for Speed

  • Under 10 Seconds: From screenshot to AI-ready image
  • 100% Local: Everything happens in your browser—no uploads, no servers
  • Privacy First: Nothing leaves your machine

📥 Installation

From Chrome Web Store (Recommended)

  1. Visit the Chrome Web Store (Link pending publication)
  2. Click "Add to Chrome"
  3. Confirm installation permissions
  4. Start capturing and annotating!

Developer Installation

  1. Download or clone this repository
  2. Open Chrome and navigate to chrome://extensions/
  3. Enable "Developer mode" in the top right
  4. Click "Load unpacked" and select the project folder
  5. The PLSFIX-THX icon will appear in your Chrome toolbar

🎯 Quick Start Guide

Basic Capture

  1. Click the PLSFIX-THX icon in your Chrome toolbar
  2. Choose "Take Screenshot" or use keyboard shortcut Alt+Shift+S
  3. Select the area you want to capture
  4. Click "Open Editor" to start annotating

Adding Annotations

  1. Click anywhere on your image to place a numbered annotation
  2. Enter your note in the sidebar
  3. Drag annotations to reposition them
  4. Mark annotations as complete when finished

Exporting Your Work

  1. Click the "Export" button in the toolbar
  2. Choose your preferred format (PDF, PNG, HTML)
  3. Your annotated screenshot is ready to share!

🎨 Screenshots & Demo

Demo screenshots and GIFs will be added here to showcase the extension in action

  • Screenshot of the main editor interface
  • GIF showing annotation placement and editing
  • Example of exported PDF with professional layout
  • Before/after comparison of annotated screenshots

❓ Frequently Asked Questions

Which AI tools work with this?

Any AI that accepts images. ChatGPT, Claude, Gemini, Cursor, Windsurf—if it has vision capabilities, it works. Just export your annotated screenshot and paste it into your AI chat.

How is this different from just taking a regular screenshot?

Regular screenshots require you to type out "see that button on the left, below the header, next to the icon..." With numbered annotations, you just say "fix the issue at #1" or "change #2 to blue." Your AI sees exactly what you mean.

Do I need the Pro version to use this with AI?

Nope. The free version gives you 5 annotated screenshots per day, which is plenty for most developers. Upgrade to Pro for unlimited screenshots and watermark-free exports.

Does this work on any website?

Yes. Capture screenshots from any website you're viewing. Perfect for debugging your own apps, reporting issues, or getting design feedback from your AI.

Are my screenshots stored securely?

All screenshots and annotations are stored locally in your Chrome browser. Nothing is uploaded to external servers, ensuring your privacy and security.

🔧 Keyboard Shortcuts

  • Alt+Shift+S: Area selection screenshot
  • Alt+Shift+F: Full page screenshot
  • F1 or ?: Show help modal with all shortcuts
  • Escape: Close dialogs and exit selection mode
  • Delete: Remove selected annotation
  • Tab: Navigate between annotations

Press F1 in the editor for the complete list of keyboard shortcuts

🛠️ Technical Specifications

  • Permissions: tabs, storage, activeTab, scripting
  • Browser Support: Chrome 88+ (Manifest V3)
  • Storage: Local Chrome storage (no external servers)
  • Performance: Optimized for large images with efficient rendering

📞 Support & Contact

Need Help?

Contributing

We welcome contributions! Please check our Contributing Guidelines and submit pull requests.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

Ready to give your AI agent perfect context? Install the free Chrome extension and start shipping faster today.