skills.rest
MLT-OSS
MLT-OSSOFFICIAL
Explore all skills by this author →
WebsiteGitHub

dogfood

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

14|5|Updated Apr 9, 2026
Search Tags:#screenshots#browser automation#web testing#bug report#issue triage#exploratory testing#qa testing
One-click install
npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill dogfood-mlt-oss
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/MLT-OSS/hermes-agent-go/tree/main/skills/dogfood
Command: npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill dogfood-mlt-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manual exploratory QA testing 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 — covering navigation, forms, console errors, and edge cases. - Evidence Capture: Takes annotated screenshots and records console errors for every issue found, with steps to reproduce. - Structured Reporting: Classifies issues by severity (Critical/High/Medium/Low) and category (Functional/Visual/Accessibility/Console/UX/Content), then generates a Markdown report with an executive summary and summary table. - Use Case: Point the agent at a staging URL before a release; it clicks through key user flows, logs a broken checkout button as Critical with a screenshot, and delivers a prioritized bug report. ## Quick Start Run a dogfood QA test 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 application?▼

Provide a target URL and testing scope, then the skill follows a 5-phase workflow: plan a sitemap, explore pages with browser tools, collect screenshot evidence, categorize issues, and generate a structured Markdown report.

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, or Content) based on 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 skill requires browser_navigate, browser_snapshot, browser_click, browser_type, browser_vision, browser_console, browser_scroll, browser_back, and browser_press. Without this toolset available, the testing workflow cannot run.

Can automated QA testing detect JavaScript console errors?▼

Yes. The workflow checks browser_console after every navigation and significant interaction, capturing uncaught exceptions, failed network requests, and deprecation warnings as evidence for Console-category issues.

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

It only covers what is reachable through the browser UI from the given entry point. Areas behind authentication walls, payment gateways, or blocked flows are listed as blockers in the report's Testing Coverage section.

Related Skills

Explore More Software Engineering Skills→
apeejay-educationapeejay-education

canary

Monitor live URLs for console errors, performance regressions, and page failures.

Official
Advanced
PostalocityPostalocity
1

bug-triage

Analyze bug reports and stack traces to identify root causes and assign ownership.

Official
Intermediate
Hack23Hack23
9

playwright-testing

Automate end-to-end browser testing for static websites with Playwright.

Official
Advanced
fryanpanfryanpan

qa-delegate

Delegates browser UI verification walks to a Sonnet subagent using written test plans.

Community
Basic