AI agent skill

Agent Browser CLI

Give an agent a headed or headless browser CLI to open pages, snapshot the DOM, and click through flows without a separate MCP server.

·

When to use this skill

Use Agent Browser CLI when the agent must look at a live page — a staging URL, a docs site, a local dev server — and act on what it sees.

When not to use it

Use Web App Testing when you already have Playwright tests to extend. Use MCP Builder if the team needs a long-lived, authenticated browser tool server.

How to install

  1. Personal install: create ~/.claude/skills/agent-browser-cli/SKILL.md (and any bundled scripts) so Claude Code, Claude Desktop, and compatible agents can load it in every project.
  2. Project install: commit the same folder at .claude/skills/agent-browser-cli/ so teammates get the skill with the repo.
  3. Restart the agent session after copying files so it re-scans the skills directory, then ask for the task in words that match the skill description.

Full install guide for Claude, Cursor, and Codex

What this skill does

This is the successor shape of the old "agent-browser-cli-browser-automation" slug: a CLI the agent shells out to, not a disappearing URL.

Intended uses

  • Confirm a deploy actually rendered
  • Extract a table from a page with no API
  • Reproduce a UI bug the stack trace cannot show

Related skills

Related skills in this directory, for comparison before you install another skill.

coding

Web App Testing

Drive a real browser against a local or deployed web app: click, type, assert visible state — not just unit tests of components.

View skill

coding

MCP Builder

Design and implement Model Context Protocol servers so an agent can call external tools with typed schemas instead of stuffing API docs into a skill.

View skill

coding

Systematic Debugging

A root-cause debugging loop for coding agents: reproduce, isolate, hypothesize, then change one thing — instead of shotgun patches.

View skill

Ranked Claude skills