dogfood

Explore web applications and document issues with reproducible evidence.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/Chris-Maskey/opencode-config --skill dogfood-chris-maskey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dogfood
Source: https://github.com/Chris-Maskey/opencode-config/tree/main/skills/dogfood
Command: npx skills add https://github.com/Chris-Maskey/opencode-config --skill dogfood-chris-maskey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Systematically explore a web application to discover usability, functional, and stability issues and produce reproducible, handoff-ready evidence for responsible teams.

Core Features & Use Cases

  • Systematic exploration: Navigate top-level sections, exercise interactive flows, and check edge cases to surface real-world problems.
  • Repro-first evidence: Capture annotated screenshots, step-by-step screenshots, and timed repro videos for interactive issues so findings can be replayed.
  • Authentication & session management: Sign in, save session state, and reuse credentials when testing gated areas.
  • Report generation: Populate a structured report template with ISSUE-### blocks, severity counts, and links to screenshots/videos for direct team handoff.
  • Use case: Run a focused dogfood session on a billing page to find and document payment flow regressions with video repros and console error captures.

Quick Start

Start a dogfood session for the target URL using agent-browser with a named session and save outputs to the dogfood-output directory.

Frequently Asked Questions about dogfood

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Can I test authenticated areas and manage sessions when dogfooding a web application?

Yes, dogfooding web applications supports signing in, saving session state, and reusing credentials when testing gated areas to ensure continuous access to protected workflows.

What is the best way to generate handoff-ready QA reports for discovered regressions?

The best way to generate handoff-ready QA reports is populating a structured report template with ISSUE-### blocks, severity counts, and links to screenshots and videos for direct team handoff.

Do I need a browser automation client to run exploratory QA and bug-hunting sessions?

Yes, exploratory QA and bug-hunting sessions require a browser automation client like agent-browser, session management, screenshot and video capture, and a report template to produce step-by-step repros.

How do I systematically explore a web application to find usability and functional issues?

Systematically explore a web application by navigating top-level sections, exercising interactive flows, and checking edge cases to surface real-world usability, functional, and stability problems across staging and production-like sites.

Does exploratory testing work with interactive workflows on staging and production-like sites?

Yes, exploratory testing applies to dogfooding and bug-hunting sessions across staging and production-like sites where authentication, navigation, and interactive workflows must be fully exercised.