agentation-self-driving

Installation
Summary

Autonomous design critique mode that adds annotations to web pages via the Agentation toolbar in a visible browser.

  • Requires the Agentation toolbar installed on the target page and the agent-browser skill available; launches in headed mode so users watch the agent scan, hover, and annotate in real time
  • Uses coordinate-based mouse events to trigger annotation dialogs (standard element clicks do not work); includes helper patterns for scrolling, bounding box lookup, and dialog interaction via eval
  • Generates 5–8 annotations per page with specific, actionable critiques (2–3 sentences max) covering hero sections, navigation, typography hierarchy, spacing rhythm, CTAs, and visual emphasis
  • Supports two-session workflows where annotations auto-send via MCP to a listening agent that implements fixes in parallel
SKILL.md

Agentation Self-Driving Mode

Autonomously critique a web page by adding design annotations via the Agentation toolbar — in a visible headed browser so the user can watch the agent work in real time, like watching a self-driving car navigate.

Launch — Always Headed

The browser MUST be visible. Never run headless. The user watches you scan, hover, click, and annotate.

Preflight: Verify agent-browser is available before anything else:

command -v agent-browser >/dev/null || { echo "ERROR: agent-browser not found. Install the agent-browser skill first."; exit 1; }

Launch: Try opening directly first. Only close an existing session if the open command fails with a stale session error — this avoids killing a browser someone else is using:

Related skills
Installs
3.9K
GitHub Stars
3.6K
First Seen
Feb 15, 2026