opencode: move android stuff to android-ui skill

home-manager/progs/opencode.nix

@@ -86,6 +86,77 @@ in
   xdg.configFile."opencode/plugins/opencode-claude-bridge.js".source =
     "${opencode-claude-bridge}/lib/opencode-claude-bridge/dist/index.js";
 
+  xdg.configFile."opencode/skills/android-ui.md".text = ''
+    ---
+    name: android-ui
+    description: "Android UI automation via ADB - use for any Android device interaction, UI testing, screenshot analysis, element coordinate lookup, and gesture automation."
+    ---
+
+    # Android UI Interaction Workflow
+
+    ## 1. Taking Screenshots
+    ```
+    adb exec-out screencap -p > /tmp/screen.png
+    ```
+    Captures the current screen state as a PNG image.
+
+    ## 2. Analyzing Screenshots
+    Delegate screenshot analysis to an explore agent rather than analyzing images directly:
+    ```
+    mcp_task(subagent_type="explore", prompt="Analyze /tmp/screen.png. What screen is this? What elements are visible?")
+    ```
+    The agent describes the UI, identifies elements, and estimates Y coordinates.
+
+    ## 3. Getting Precise Element Coordinates
+    UI Automator dump - extracts the full UI hierarchy as XML:
+    ```
+    adb shell uiautomator dump /sdcard/ui.xml && adb pull /sdcard/ui.xml /tmp/ui.xml
+    ```
+    Then grep for specific elements:
+    ```sh
+    # Find by text
+    grep -oP 'text="Login".*?bounds="[^"]*"' /tmp/ui.xml
+    # Find by class
+    grep -oP 'class="android.widget.EditText".*?bounds="[^"]*"' /tmp/ui.xml
+    ```
+    Bounds format: `[left,top][right,bottom]` — tap center: `((left+right)/2, (top+bottom)/2)`
+
+    ## 4. Tapping Elements
+    ```
+    adb shell input tap X Y
+    ```
+    Where X, Y are pixel coordinates from the bounds.
+
+    ## 5. Text Input
+    ```
+    adb shell input text "some_text"
+    ```
+    Note: Special characters need escaping (`\!`, `\;`, etc.)
+
+    ## 6. Other Gestures
+    ```sh
+    # Swipe/scroll
+    adb shell input swipe startX startY endX endY duration_ms
+    # Key events
+    adb shell input keyevent KEYCODE_BACK
+    adb shell input keyevent KEYCODE_ENTER
+    ```
+
+    ## 7. WebView Limitation
+    - UI Automator can see WebView content if accessibility is enabled
+    - Touch events on iframe content (like Cloudflare Turnstile) often fail due to cross-origin isolation
+    - Form fields in WebViews work if you get exact bounds from the UI dump
+
+    ## Typical Flow
+    1. Take screenshot → analyze with explore agent (get rough layout)
+    2. Dump UI hierarchy → grep for exact element bounds
+       - NEVER ASSUME COORDINATES. You must ALWAYS check first.
+       - Do this before ANY tap action as elements on the screen may have changed.
+    3. Calculate center coordinates from bounds
+    4. Tap/interact
+    5. Wait → screenshot → verify result
+  '';
+
   xdg.configFile."opencode/skills/playwright.md".text =
     let
       browsers = pkgs.playwright-driver.browsers;
@@ -140,56 +211,6 @@ in
       ## Nix
       For using `nix build` append `-L` to get better visibility into the logs.
       If you get an error that a file can't be found, always try to `git add` the file before trying other troubleshooting steps.
-
-
-      ## Android UI Interaction Workflow Summary
-      1. Taking Screenshots
-      adb exec-out screencap -p > /tmp/screen.png
-      Captures the current screen state as a PNG image.
-
-      2. Analyzing Screenshots
-      I delegate screenshot analysis to an explore agent rather than analyzing images directly:
-      mcp_task(subagent_type="explore", prompt="Analyze /tmp/screen.png. What screen is this? What elements are visible?")
-      The agent describes the UI, identifies elements, and estimates Y coordinates.
-
-      3. Getting Precise Element Coordinates
-      UI Automator dump - extracts the full UI hierarchy as XML:
-      adb shell uiautomator dump /sdcard/ui.xml && adb pull /sdcard/ui.xml /tmp/ui.xml
-      Then grep for specific elements:
-      # Find by text
-      grep -oP 'text="Login".*?bounds="[^"]*"' /tmp/ui.xml
-      # Find by class
-      grep -oP 'class="android.widget.EditText".*?bounds="[^"]*"' /tmp/ui.xml
-      Bounds format: [left,top][right,bottom] → tap center: ((left+right)/2, (top+bottom)/2)
-
-      4. Tapping Elements
-      adb shell input tap X Y
-      Where X, Y are pixel coordinates from the bounds.
-
-      5. Text Input
-      adb shell input text "some_text"
-      Note: Special characters need escaping (\!, \;, etc.)
-
-      6. Other Gestures
-      # Swipe/scroll
-      adb shell input swipe startX startY endX endY duration_ms
-      # Key events
-      adb shell input keyevent KEYCODE_BACK
-      adb shell input keyevent KEYCODE_ENTER
-
-      7. WebView Limitation
-      - UI Automator can see WebView content if accessibility is enabled
-      - Touch events on iframe content (like Cloudflare Turnstile) often fail due to cross-origin isolation
-      - Form fields in WebViews work if you get exact bounds from the UI dump
-
-      Typical Flow
-      1. Take screenshot → analyze with explore agent (get rough layout)
-      2. Dump UI hierarchy → grep for exact element bounds
-         - NEVER ASSUME COORDINATES. You must ALWAYS check first.
-         - Do this before ANY tap action as elements on the screen may of changed.
-      3. Calculate center coordinates from bounds
-      4. Tap/interact
-      5. Wait → screenshot → verify result
     '';
     settings = {
       theme = "opencode";