dogfood

Explore web apps with agent-browser to identify bugs and generate reproduction reports.

9|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/gwenwindflower/dotfiles --skill dogfood-gwenwindflower
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/gwenwindflower/dotfiles/tree/main/dot_agents/exact_skills/dogfood
Command: npx skills add https://github.com/gwenwindflower/dotfiles --skill dogfood-gwenwindflower

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Systematically explore a web app via agent-browser to identify bugs and UX issues and produce a reproduction-rich report, enabling rapid QA, dogfooding, or testing.

Core Features & Use Cases

  • Systematic web app exploration to surface bugs, UX problems, and regression risks.
  • Generates a structured dogfood report with reproduction evidence (screenshots, videos, and steps).
  • Supports configurable session names, target URLs, and scope for focused testing.

Quick Start

Initiate a named agent-browser session against the target URL and let the agent autonomously explore, capture evidence, and generate a report.

Frequently Asked Questions about dogfood

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate QA testing to find UX issues in a web app?

Automate QA testing by deploying an agent-browser to systematically explore your web app, identify UX issues, and produce a structured report with reproduction steps, screenshots, and videos.

Can I generate bug reproduction reports automatically during web app dogfooding?

Yes, you can generate bug reproduction reports automatically. The agent-browser captures evidence like screenshots and steps while exploring your target URL, producing a structured dogfood report.

How does systematic web app exploration work for finding regression risks?

Systematic web app exploration works by letting an agent-browser autonomously navigate a target URL, interact with elements, and capture evidence to surface bugs, UX problems, and regression risks.

Do I need agent-browser to run automated bug testing on my web application?

Yes, agent-browser is required. It provides the autonomous browser interaction needed to explore the target URL, capture reproduction evidence, and generate the structured dogfood report.

Can I configure the testing scope and session name for web app QA?

Yes, you can configure the session name, target URL, and testing scope. This allows you to focus the autonomous agent-browser exploration on specific areas of your web app during QA.

What is the best way to document bugs found during browser-based testing?

The best way to document bugs is using a structured dogfood report. It autonomously captures reproduction evidence including screenshots, videos, and step-by-step instructions for every identified issue.