dogfood

Tests web applications via browser automation and generates structured bug reports.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill dogfood-avatar-arts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/AvaTar-ArTs/.Agent-skills/tree/main/skills/dogfood
Command: npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill dogfood-avatar-arts

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 provides a systematic five-phase workflow for finding, evidencing, and reporting web app defects. ## Core Features & Use Cases - Systematic Exploration: Navigates pages, clicks elements, fills forms, and checks the JavaScript console after every interaction to catch silent errors. - Evidence Collection: Captures annotated screenshots for every issue and classifies findings using a severity and category taxonomy (Critical through Low; Functional, Visual, Accessibility, Console, UX, Content). - Structured Reporting: De-duplicates issues, sorts them by severity, and generates a complete Markdown report with an executive summary, per-issue details, and a summary table. - Use Case: Point the Skill at a staging URL before a release, and it will crawl key user flows, document a broken checkout button with a screenshot and console errors, and deliver 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 exploratory QA testing on a web application?

Provide a target URL, a testing scope such as specific features or full site, and optionally an output directory. The Skill follows a five-phase workflow: plan a sitemap, explore pages with browser tools, collect screenshot evidence, categorize issues by severity, and generate a Markdown report.

How to find JavaScript errors while testing a website?

Check the browser console after every navigation and significant interaction using the browser_console tool. Silent uncaught exceptions, failed network requests, and unhandled promise rejections are high-value findings that get recorded in the bug report.

What browser tools are required for automated web QA testing?

The Skill requires a browser toolset including 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 by severity in QA reports?

Issues are classified as Critical, High, Medium, or Low based on impact, and categorized as Functional, Visual, Accessibility, Console, UX, or Content. Critical issues make core features unusable or cause data loss, while Low issues are minor polish problems like typos.

What are the limitations of automated exploratory browser testing?

Testing is limited to what the browser toolset can reach and observe, so areas behind unavailable credentials or blocked flows become documented blockers. The Skill records untested areas and blockers in the report's coverage section rather than guaranteeing full coverage.