dogfood

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

Updated May 28, 2026
One-click install
npx skills add https://github.com/patty-chow/the-stable --skill dogfood-patty-chow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/patty-chow/the-stable/tree/main/skills/dogfood
Command: npx skills add https://github.com/patty-chow/the-stable --skill dogfood-patty-chow

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 runs a systematic five-phase browser-based testing workflow that finds issues, captures evidence, and produces a structured bug report. ## Core Features & Use Cases - Systematic Exploration: Navigates pages, clicks elements, fills forms, and checks the JavaScript console after every interaction to surface silent errors. - Evidence Collection: Captures annotated screenshots for every issue and classifies findings by severity (Critical to Low) and category (Functional, Visual, Accessibility, Console, UX, Content) using a defined taxonomy. - Structured Reporting: Generates a report with an executive summary, per-issue reproduction steps, a summary table, and testing coverage notes. - Use Case: Point it at a staging URL before a release and receive a prioritized bug report with screenshot evidence for every issue found. ## 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 such as specific features or full site, and optionally an output directory. The workflow plans a sitemap, explores pages with browser tools, collects screenshot evidence, and generates a structured 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 the taxonomy in references/issue-taxonomy.md, then sorted by severity in the final report.

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 every navigation and interaction catch silent JavaScript errors.

What does the generated QA bug report include?▼

The report includes an executive summary with severity counts, per-issue sections with reproduction steps and screenshot references, a summary table, and testing coverage notes listing pages tested, features exercised, and blockers.

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

It depends on the availability of the browser toolset and only covers areas within the defined scope. Areas blocked by authentication failures or other blockers are documented in the report as not tested rather than verified.