dogfood

Tests web applications through browser automation and generates structured bug reports with screenshots.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/raulisai/eva02 --skill dogfood-raulisai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/raulisai/eva02/tree/main/apps/eva-core/src/skills/dogfood
Command: npx skills add https://github.com/raulisai/eva02 --skill dogfood-raulisai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manual exploratory QA of web applications is slow and inconsistent, and bugs often go undocumented without screenshots, reproduction steps, or severity classification. This Skill automates systematic browser-based testing and produces a structured, evidence-backed bug report. ## Core Features & Use Cases - Systematic 5-Phase QA Workflow: Plan a sitemap, explore pages with browser tools, collect screenshot evidence, categorize issues, and generate a final report. - Issue Taxonomy: Classifies every finding by severity (Critical/High/Medium/Low) and category (Functional, Visual, Accessibility, Console, UX, Content) using a defined reference taxonomy. - Console Error Detection: Checks JavaScript console output after every navigation and interaction to surface silent errors. - Use Case: Point the Skill at a staging URL before a release; it navigates key flows, tests forms with valid and invalid inputs, captures annotated screenshots of defects, and outputs a report.md with an executive summary and per-issue reproduction steps. ## Quick Start Run exploratory QA on https://staging.myapp.com covering the signup and checkout flows and save the report to ./dogfood-output.

Frequently Asked Questions about dogfood

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

FAQPage Schema
How do I run automated exploratory QA on a web application?

Provide a target URL, a testing scope, and an optional output directory. The Skill plans a sitemap, navigates pages with browser tools, tests interactive elements and forms, captures screenshots of issues, and writes a structured report to report.md.

What tools are needed for browser-based QA testing with this workflow?

The workflow requires a browser toolset exposing browser_navigate, browser_snapshot, browser_click, browser_type, browser_vision, browser_console, browser_scroll, browser_back, and browser_press. These cover navigation, DOM inspection, interaction, screenshots, and console monitoring.

How are bugs classified in the QA report?

Each issue is assigned a severity (Critical, High, Medium, Low) and a category (Functional, Visual, Accessibility, Console, UX, Content) based on the taxonomy in references/issue-taxonomy.md. Issues are de-duplicated and sorted by severity in the final report.

Can this detect JavaScript errors that don't break the page visually?

Yes. The workflow calls browser_console after every navigation and significant interaction, specifically to catch silent uncaught exceptions, failed network requests, and deprecation warnings that produce no visible symptoms.

What are the limitations of automated exploratory browser testing?

It depends on the availability of the browser toolset and cannot execute areas blocked by authentication or environment blockers, which are recorded in the report's Blockers section. It also does not replace load testing, security penetration testing, or unit-level test coverage.