dogfood

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

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/CHENHUI-X/toolbox --skill dogfood-chenhui-x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/CHENHUI-X/toolbox/tree/main/official-skills/software-development/dogfood
Command: npx skills add https://github.com/CHENHUI-X/toolbox --skill dogfood-chenhui-x

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 by severity and category, and generate a final report. - Issue Taxonomy: Classifies findings by severity (Critical/High/Medium/Low) and category (Functional, Visual, Accessibility, Console, UX, Content) using a defined reference taxonomy. - Structured Report Generation: Produces a Markdown report with an executive summary, per-issue reproduction steps, console errors, and inline screenshot evidence. - Use Case: Point the agent at a staging URL before a release; it navigates key user flows, tests forms with valid and invalid inputs, captures JavaScript console errors, and delivers a prioritized bug report. ## Quick Start Run exploratory QA testing on https://staging.example.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 testing on a web app?

Provide a target URL, a testing scope, and an optional output directory. The agent follows a 5-phase workflow: plan a sitemap, explore pages with browser tools, collect screenshot evidence, categorize issues, and generate a Markdown bug report.

How are bugs classified in a QA report?

Issues are classified by severity (Critical, High, Medium, Low) and category (Functional, Visual, Accessibility, Console, UX, Content) using a defined taxonomy. Reports are sorted by severity with counts summarized in an executive summary table.

What browser tools are required for automated web testing?

The workflow requires browser_navigate, browser_snapshot, browser_click, browser_type, browser_vision, browser_console, browser_scroll, browser_back, and browser_press. Console checks after each navigation and interaction catch silent JavaScript errors.

Can automated QA testing detect JavaScript console errors?

Yes, the workflow checks the browser console after every navigation and significant interaction. Uncaught exceptions, failed network requests, and deprecation warnings are recorded as findings with severity based on impact.

What are the limitations of exploratory browser-based QA?

It depends on the availability of the browser toolset and only covers pages reachable through navigation and interaction. Areas behind authentication walls or untested flows are documented as out of scope in the report's coverage section.