agentation-self-driving

This skill enables an AI agent to perform autonomous design critiques on web pages by interacting with the Agentation annotation toolbar in a headed browser. It follows a structured workflow to scroll, identify elements, calculate coordinates, and submit design feedback.

5.2K
Installs
4
Use cases
5/10
Quality

Is agentation-self-driving safe to install?

Review the source first

Review the source first: our audit of agentation-self-driving's source files found 16 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands via agent-browser and performs coordinate-based mouse interactions on live web pages. It requires the agent-browser skill to be installed and active.

How we audit skills: our security review methodology.

Who is this skill for?

Developers and designers using Claude Code who want to automate UI/UX review processes by having an agent navigate a web page and leave actionable design annotations.

What can you do with it?

  • Autonomously critiquing web page layouts and UI components.
  • Adding design feedback annotations to specific page elements.
  • Verifying design implementation against visual hierarchy and spacing principles.
  • Coordinating with a second agent session to implement design fixes based on submitted annotations.

How good is this skill?

Quality score: 5/10. The documentation is highly specific, providing clear command patterns and troubleshooting steps for common pitfalls like @ref limitations and browser session management.

What does the skill file contain?

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:

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

**Lau...

Frequently asked questions

Does this skill work in headless mode?

No. The skill requires a headed browser session so the user can observe the agent navigating and annotating the page.

Why do coordinate-based clicks replace standard @ref clicks?

The Agentation overlay intercepts pointer events at the coordinate level. Standard @ref clicks may bypass the overlay and interact with the underlying DOM instead.

How do I handle annotation dialogs that do not appear?

Verify the toolbar is expanded using the state-aware eval command. If it collapsed, re-expand it and retry the interaction.

What should I do if the annotation count does not increase after submission?

The submission likely failed. Re-snapshot the page to check if the dialog remains open, then verify the input fields.

Data sourced from benjitaylor/agentation on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

find-skills

2.3M

Users seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages

The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.

highclipackage-managervercel-labs

frontend-design

618.4K

AI agents tasked with designing and building web interfaces who need to produce unique, high-quality visual identities rather than generic, templated designs

The frontend-design skill provides guidance for creating distinctive, intentional visual designs for web interfaces. It instructs the agent to act as a design lead at a small studio, focusing on avoiding templated defaults by making deliberate choices regarding typography, color palettes, layout, and motion. The skill emphasizes a structured process of brainstorming, planning, and self-critique before writing code.

nonedesignfrontendanthropics

agent-browser

506.7K

AI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications

The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.

highbrowser-automationclivercel-labs

image-to-video

355.0K

Developers and users who need to automate video generation from images using the RunComfy platform

The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.

highaivideo-generationagentspace-so