What problem does it solve?
Tauri v2 applications use system WebViews (WebKitGTK on Linux, WebKit on macOS, WebView2 on Windows) instead of Chromium, making standard web automation tools like Playwright incompatible. This skill solves that by providing a CLI and debug plugin that communicate over Unix sockets or Named Pipes using JSON-RPC 2.0, enabling AI agents and developers to inspect, interact with, and debug Tauri app UIs in real-time.
Core Features & Use Cases
- UI Inspection: Capture accessibility snapshots of interactive elements with stable references for precise targeting and minimal token usage.
- Interaction Automation: Click, fill, type, select, check, scroll, drag, and drop elements using refs, CSS selectors, or coordinates.
- Verification & Debugging: Assert element state, wait for conditions, watch DOM mutations, capture screenshots, and inspect console logs and network requests.
- Use Case: An AI agent can snapshot a Tauri app's dashboard, identify a filter input by its ref, fill it with a search term, press Enter, wait for results to load, and assert the correct number of results appears.
Quick Start
Use the tauri-pilot skill to inspect the running Tauri app by taking an interactive snapshot, then click the element with ref @e3 and verify the result with an assertion.