This skill drives browser-based UI validation by executing agent-browser commands to open pages, perform interactions, and capture DOM evidence for Ralph tasks.
npx playbooks add skill lambda-curry/devagent --skill agent-browser
Use Agent Browser to configure Claude Code, Cursor, or Copilot for testing & qa: it this skill drives browser-based ui validation by executing agent-browser commands to open pages, perform interactions, and capture dom evidence for ralph tasks.
This compact 22-word instruction set is purpose-built for testing & qa work in AI coding agents. Install with a single command.
This skill drives browser-based UI validation by executing agent-browser commands to open pages, perform interactions, and capture DOM evidence for Ralph tasks.
Agent Browser is a free testing & qa skill for AI coding agents. This skill drives browser-based UI validation by executing agent-browser commands to open pages, perform interactions, and capture DOM evidence for Ralph tasks.. It provides a specialized system prompt that configures your agent with testing & qa expertise.
Run npx playbooks add skill lambda-curry/devagent --skill agent-browser in your terminal to install Agent Browser into your Claude Code session. It works immediately after installation.
Agent Browser is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Yes, Agent Browser is completely free and open source. The full source is available on GitHub at https://github.com/lambda-curry/devagent/tree/main/.devagent/plugins/ralph/skills/agent-browser. You only need a subscription to the AI agent you use it with.
Weekly roundup of top Claude Code skills, MCP servers, and AI coding tips.