dogfood

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

5|2|Updated May 26, 2026
One-click install
npx skills add https://github.com/perasyudha/Nyxora --skill dogfood-perasyudha
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/perasyudha/Nyxora/tree/main/packages/core/playbooks/dogfood
Command: npx skills add https://github.com/perasyudha/Nyxora --skill dogfood-perasyudha

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. ## Core Features & Use Cases - Systematic 5-Phase Workflow: Plan, explore, collect evidence, categorize, and report issues across pages, forms, and user flows. - Evidence Capture: Takes annotated screenshots and reads browser console output to surface silent JavaScript errors. - Structured Bug Reports: Classifies issues by severity (Critical to Low) and category (Functional, Visual, Accessibility, Console, UX, Content) using a defined taxonomy and report template. - Use Case: Point the agent at a staging URL before release; it navigates the site, tests forms with valid and invalid inputs, captures console errors, and produces a prioritized report.md with screenshot evidence. ## 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 and testing scope, then the agent follows a 5-phase workflow: plan a sitemap, explore pages with browser navigation and clicks, collect screenshot evidence, categorize issues by severity, and generate a structured report.md.

How to find JavaScript console errors during website testing?

The workflow checks the browser console after every navigation and significant interaction using the browser_console tool. Silent uncaught exceptions and failed network requests are captured and classified as high-value findings in the report.

What browser tools are required for automated web QA?

The skill requires a browser toolset with browser_navigate, browser_snapshot, browser_click, browser_type, browser_vision, browser_console, browser_scroll, browser_back, and browser_press. Without these tools available, the testing workflow cannot execute.

How are bugs classified in the QA report?

Issues are 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, then sorted Critical-first in the final report.

What are the limitations of automated exploratory browser testing?

Testing is limited to what the browser toolset can reach and observe; areas behind authentication it cannot complete, CAPTCHAs, or blocked flows are recorded as blockers in the report. It does not execute load testing or deep security scanning.