Agentation Self Driving

You know how design feedback usually happens in Figma comments or Loom videos after the fact? This runs the critique live in a headed browser while you watch Claude mouse around your actual page like a self-driving car, clicking elements and adding annotations through the Agentation toolbar. It scrolls, calculates bounding boxes, moves the cursor to center points, and fills out annotation dialogs with specific critiques referencing visual hierarchy and spacing patterns. The annotations pile up as numbered markers on the page. Best for when you want actionable UI feedback on a live site and want to see the agent work rather than just get a markdown list back. Needs the Agentation toolbar already installed on your page and the agent-browser skill.

skills.sh installs: 7.1K
GitHub stars: 5.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add benjitaylor/agentation --skill agentation-self-driving --agent claude-code

Installs into .claude/skills of the current project.

Files

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:

# Try to open. If it fails (stale session), close first then retry.
agent-browser --headed open <url> 2>&1 || { agent-browser close 2>/dev/null; agent-browser --headed open <url>; }

Then verify the Agentation toolbar is present and expand it:

SKILL.md on GitHub