dogfood

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

Updated Jun 30, 2026
One-click install
npx skills add https://github.com/zhoulingxiao1216/testworkspace --skill dogfood-zhoulingxiao1216
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/zhoulingxiao1216/testworkspace/tree/main/all_Skills/dogfood
Command: npx skills add https://github.com/zhoulingxiao1216/testworkspace --skill dogfood-zhoulingxiao1216

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 that navigates a target site, interacts with elements, captures evidence, and produces a structured bug report. ## Core Features & Use Cases - Systematic Exploratory Testing: Plans a sitemap, navigates pages, clicks elements, fills forms, and checks the JavaScript console after every interaction to surface silent errors. - Evidence Collection & Classification: Captures annotated screenshots for every issue and classifies findings by severity (Critical/High/Medium/Low) and category (Functional/Visual/Accessibility/Console/UX/Content) using a defined taxonomy. - Structured Test Execution Support: Handles formal test-case handoffs with an environment gate, queue parsing, and blocking reports when prerequisites fail, avoiding fabricated results. - Use Case: Point the Skill at a staging URL for a new checkout flow; it explores the pages, discovers that the submit button silently fails, captures a screenshot and console error, and delivers a prioritized report.md with reproduction steps. ## Quick Start Run exploratory QA testing on https://staging.example.com focusing on 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 and a testing scope such as specific features or full site coverage. The workflow plans a sitemap, navigates pages, interacts with elements, checks the console for errors, and generates a structured bug report with screenshots.

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. Critical issues break core features or cause data loss, while Low issues are minor polish problems.

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. The vision tool with annotate=true labels interactive elements for targeted clicking and typing.

Can this execute a formal test-case set instead of exploratory testing?▼

Yes, structured test execution loads project-specific specs, parses a case queue or manifest, and runs an environment gate covering URL reachability, login, and test data. If the gate fails, it halts with a blocking report rather than guessing results.

What happens when the test environment is unreachable?▼

Execution halts and a blocking report is created with parsed case counts, gate check evidence, the blocking reason, and recovery conditions. Cases are marked Blocked rather than Pass or Fail, and no screenshots or defects are fabricated.