edit docker files, add skill of browser-use in the workdir

docker/chromium-gui/README.md

@@ -0,0 +1,26 @@
+# Chromium GUI Service
+
+This container provides a full Chromium GUI with three interfaces:
+
+- noVNC web UI: `http://localhost:6080/vnc.html`
+- VNC: `localhost:5900`
+- CDP endpoint: `http://localhost:9223/json/version`
+
+## Run
+
+```bash
+docker compose --profile gui up -d chromium-gui
+```
+
+## Use with browser-use
+
+Pass the GUI CDP endpoint as HTTP URL (the runner resolves it to a websocket automatically):
+
+```bash
+docker compose exec -T hermes-agent python-browser-use \
+  /root/.hermes/skills/autonomous-ai-agents/browser-use/scripts/run_browser_use.py \
+  --cdp-url http://chromium-gui:9223 \
+  --task "Open example.com and return page title" \
+  --max-steps 5
+```
+