← ClaudeAtlas

computer-uselisted

Inspect and operate desktop application windows through the bundled Python wrapper around cua-driver. Use when the user explicitly asks the Agent to interact with a graphical application and ordinary vBot Tools cannot perform the task. Prefer browser-use for web pages and ordinary Tools for files, processes, and configuration.
Vironnimo/vbot · ★ 1 · AI & Automation · score 77
Install: claude install-skill Vironnimo/vbot
# Computer Use Use the bundled Python script to inspect and operate application windows on the machine running the vBot server. This is a script-backed prototype, not a built-in Tool. On a remote Pi-server plus Windows Desktop Client setup it controls the Pi desktop, not the user's Windows Desktop Client. The wrapper uses `cua-driver`'s one-shot CLI transport. It requests background delivery by default, but actual behavior and supported applications depend on the host platform and installed driver version. ## Script contract - Run `python {baseDir}/scripts/computer_use.py --session <session> doctor` before the first desktop action in a task. - Choose a unique lowercase session name containing only letters, digits, hyphens, or underscores. Reuse it for the complete task and call `start` once before inspection. - Treat stdout JSON as data. Exit code zero with `"ok": true` means the operation completed. A nonzero exit or `"ok": false` means it did not. - The script never installs or upgrades `cua-driver`. Report a missing or incompatible driver and ask before installing anything. - Captures and oversized accessibility data are written below `tmp/computer-use/<session>/` in the effective cwd. Load screenshot paths with vBot's `read` Tool. - Element actions (`click`/`scroll` with `--element`) accept an element index or an `element_token` (e.g. `s00000001:12`) from a capture. An index resolves against the session's latest capture of the same `pid`/`window_id`; capture the targe