On a dense dashboard with five buttons that look alike, my coding agent reads the screenshot, guesses which one I meant, and edits the wrong one. Then I re-explain, it tries again, another round gone.

What fixed it for me: I stopped sending the raw image. I mark the exact element, write what should change, and hand over a small structured file instead. The agent edits the right thing on the first pass, and the handoff is around 700 tokens instead of several thousand for the picture.

Curious how the makers here deal with the "which element" problem. Prompt harder? Crop tighter? Something smarter?

Pasting a screenshot into a terminal agent is messier than it should be. On macOS Codex wants Ctrl+V, not Cmd+V. Claude Code on Windows wants Alt+V. Some terminals just eat the image. So people end up saving the shot to disk and referencing the path by hand, which kills the flow.

What's your real workflow, drag and drop, the --image flag, save-and-reference, something better? Trying to map how people actually do this.

These came from people who tried the SlimSnap screenshot-to-JSON workflow during launch and asked for something specific. Listing in the order they came in.

1. Screenshot capture for scrollable content and open dropdowns. Right now the capture clips to the visible window, so if a dropdown or long list is open, parts get cut. Balpreet S flagged this on LinkedIn.

2. Native Mac app screenshot support (scope verification). Several people asked whether SlimSnap captures Linear / Notion / Figma desktop screenshots, or just browser windows. The answer changes who can use it.

3. Confidence and overlap indicators on annotations. When the arrow is ambiguous (e.g. drawn between two close buttons in the screenshot), the JSON should signal that. Corey Clark asked on LinkedIn.

4. Nested element hierarchy in the schema. Current screenshot schema is flat with bbox containment for nesting. Jyoti S Mohanty asked whether to make hierarchy explicit. Schema v2 candidate.

5. Hybrid mode (JSON + raw screenshot). For users who want the safety net of pixels alongside the structured spec. Martin Zokov asked on X. Optional, would double the per-screenshot token cost.

6. Windows screenshot support. Multiple people. OCR layer is Mac-native, so this is a real porting project, not a one-line change.

Which one should I build next? Vote in the comments, ideally with one line on why it matters for your screenshot workflow.

I have my own gut ranking but want to see what actual users prioritize.