Dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step
Overview
The Dogfood skill, part of the mxyhi/ok-skills repository, provides AI agents with a systematic framework for exploratory web application testing. It is designed to identify software bugs, user experience inconsistencies, and general functional issues by navigating through a platform's interface. Compatible with agents like Claude, Codex, and OpenClaw, this tool automates the quality assurance process by simulating user interactions. Upon completion, the skill generates a structured report that includes detailed reproduction steps and evidence for each identified problem. This resource is particularly useful for developers and QA teams looking to conduct thorough bug hunts or platform reviews without manual scripting, leveraging the popularity of its parent repository which has earned 423 stars.
Use Cases
Install Notes
# Review source first
open https://github.com/mxyhi/ok-skills/blob/main/dogfood/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
Security Notes
As a browser-based testing tool, this skill interacts with web applications to identify vulnerabilities and defects. Users should ensure the skill is only deployed on environments where automated exploration is authorized, as it systematically navigates and tests site functionality.
Related Skills
Internal Comms
anthropics/skills
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project upd...
Planning And Task Breakdown
addyosmani/agent-skills
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Notion Knowledge Capture
openai/plugins
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
Notion Spec To Implementation
openai/plugins
Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.
Notion Research Documentation
openai/plugins
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
Notion Meeting Intelligence
openai/plugins
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.