Back to Skills

agentation-self-driving

Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.

3,557stars284forksUpdated 5/8/2026

Security Assessment

Medium Risk(50/100)

Detected risks:

Remote Code Execution([SKILL.md] eval ()
Security Score50/100

About agentation-self-driving

agentation-self-driving is a reusable AI skill focused on a specific workflow. name: agentation-self-driving

The skill packages instructions, conventions, and task-specific guidance so an agent can execute the job more consistently. description: Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available. allowed-tools: Bash(agent-browser:*) 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.

In practice, this skill is best suited for users who need repeatable execution with fewer setup steps and less ambiguity. 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:

FAQ

What does agentation-self-driving help with?

agentation-self-driving helps agents follow a focused workflow described in the source documentation, reducing ambiguity and keeping execution aligned with the intended task.

When should this skill be used?

Use it when the task matches the workflow, domain, or operating rules described in the skill documentation, especially when consistent execution matters.

What are the main limitations?

The skill is constrained by the quality and scope of its source instructions. If the underlying documentation is incomplete, the agent may still need extra context or manual validation.

All Files

2 files
SKILL.md10.9 KB
View
references/two-session-workflow.md2.3 KB
View

Install agentation-self-driving

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill