dogfood

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

Updated Aug 19, 2026
One-click install
npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill dogfood-jakubbartnik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/jakubbartnik/honey-barrel-finale/tree/main/honey-barrel-finale/workspace/hermes/skills/dogfood
Command: npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill dogfood-jakubbartnik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manual exploratory QA of web applications is time-consuming and inconsistent, often missing silent JavaScript errors, broken flows, and visual defects. This Skill systematizes the process by driving a browser through the application, capturing evidence, and producing a structured bug report. ## Core Features & Use Cases - Five-phase QA workflow: Plan, Explore, Collect Evidence, Categorize, and Report, covering navigation, forms, keyboard input, scrolling, and edge cases. - Evidence capture: Takes annotated screenshots, records console errors, and documents reproduction steps for every issue found. - Standardized classification: Uses a severity (Critical/High/Medium/Low) and category (Functional/Visual/Accessibility/Console/UX/Content) taxonomy, then generates a report from a Markdown template. - Use Case: Point it at a staging URL before a release; it clicks through sign-up, login, and checkout flows, flags a broken submit button and console exceptions, and delivers a prioritized report with screenshots. ## Quick Start Run exploratory QA on https://staging.example.com covering the full site and save the report and screenshots 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 workflow plans a sitemap, navigates each page with browser tools, interacts with elements, captures screenshots and console errors, and generates a structured report at the end.

What browser tools are needed 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. These cover navigation, DOM inspection, interaction, screenshots, and console error detection.

How are bugs classified in a QA report?▼

Issues are assigned a severity (Critical, High, Medium, Low) and a category (Functional, Visual, Accessibility, Console, UX, Content) based on the included taxonomy reference. The report sorts issues by severity and summarizes counts in an executive summary.

Can automated testing detect silent JavaScript errors?▼

Yes. The workflow checks the browser console after every navigation and significant interaction, catching uncaught exceptions, failed network requests, and deprecation warnings that produce no visible page change.

What are the limitations of exploratory browser-based QA?▼

It depends on the availability of the browser toolset and only covers what it can reach through the UI. Areas behind authentication it cannot complete, performance benchmarking, and deep accessibility audits may require dedicated tools.