DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to point at a window element and send a fix request to the agent with DSH Worktable

Click a spot in a window, type the change, and load a packaged annotation into chat for the agent to act on.

Who it is forA developer reviewing a rendered window who wants to request a visual change without describing its location in words.

The problemDescribing which element to change and where it sits takes several messages and often leads to the wrong element being edited.

The outcomeThe chat input receives a packaged message with the window number, coordinates, clicked element, and your request, ready to send.

What you need first

  • A working DeepSeek Harness (dsh) install with the web profile, or the Desktop app on Windows for the tested Desktop scope
  • Node.js and npm if you plan to clone the repo and build from source
  • A browser where you can keep the same origin, since projects and layouts are stored in browser localStorage

Steps

  1. Open the window you want to change inside a project workspace.
  2. Click the small annotate button (chat bubble with a plus) in that window's title bar.
  3. Click the spot in the window where the change belongs, type your request such as "make this text bigger", and press ✓.
  4. Review the message that fills the chat input; it is not sent yet.
  5. Press Enter to send it when ready, then check the agent's result with a screenshot or the window itself.

Prompt for your agent

In the repo Aisland-SJL/dsh-worktable, a user has sent a point-to-annotate message for window <window-number> at <coordinates>. Apply the requested change to the target element, report which element was changed, and verify the result with a screenshot before finishing.

Caveat. The annotation is only filled into the chat input and is not sent automatically, so you still need to press Enter yourself.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page