agent-browser
Browser Automation with agent-browser
Use agent-browser CLI for browser automation tasks: UI checks, form testing, screenshots, visual diffs.
Requires: npm install -g agent-browser && agent-browser install
Screenshots directory
Save screenshots, PDFs and diffs to .claude/local/screenshots/ (unversioned via .claude/ gitignore).
Create the directory before first use: mkdir -p .claude/local/screenshots
agent-browser screenshot .claude/local/screenshots/page.png
agent-browser pdf .claude/local/screenshots/page.pdf
agent-browser diff screenshot --baseline .claude/local/screenshots/before.png -o .claude/local/screenshots/diff.png
Core workflow
More from jrollin/claudio
skill-testing
>
1spec-create
Create a new feature specification following a phased workflow. Use when starting a new feature that needs requirements, design, and task planning. Invoke for spec-driven development, feature specification, requirements-design-tasks workflow.
1spec-impl
Task-by-task implementer that reads a completed spec and executes each task atomically. Use when a feature spec exists and you're ready to implement. Invoke for spec implementation, task execution, spec-driven development.
1event-modeling-tasks
Use when translating a completed event model into implementation tasks. Invoke when an event model with slices and specifications exists and needs to become a development plan, task breakdown, or spec-create compatible output.
1event-modeling-spec
Use when designing systems with Event Modeling methodology, creating event models, or when user mentions event modeling, commands/events/views blueprints, system timeline design, or CQRS system design workshops.
1