dogfooding
A structured workflow for testing web apps from an end-user perspective to identify UX and functionality issues.
Install
mkdir -p .claude/skills/dogfooding && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10805" && unzip -o skill.zip -d .claude/skills/dogfooding && rm skill.zipInstalls to .claude/skills/dogfooding
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
**WORKFLOW SKILL** — Perform critical dogfooding testing of web applications, providing structured feedback on usability, fun factor, and user experience. USE FOR: testing apps as a critical user; evaluating user experience and engagement; identifying UX issues and improvement opportunities; providing actionable feedback for app development.Key capabilities
- →Simulate user journeys
- →Verify functionality
- →Analyze engagement
- →Provide structured feedback
How it works
It guides a critical evaluation of a web app by simulating user flows and assessing engagement factors against a structured template.
Inputs & outputs
When to use dogfooding
- →Evaluate application user experience
- →Perform user flow testing
- →Identify UX improvements
About this skill
Dogfooding Skill
Overview
This skill guides a thorough, critical evaluation of a web application from an end-user perspective, simulating real usage scenarios and providing structured feedback on usability, engagement, and overall user experience.
Process Steps
1. Establish Context
- Read main application files (App.tsx, main components)
- Understand core data structures and game logic
- Review styling and UI components
- Check configuration and build setup
2. Verify Functionality
- Run unit tests to ensure basic functionality
- Build the application for production
- Launch development server and verify startup
- Check for console errors or build warnings
3. Simulate User Journeys
- Walk through primary user flows (start → play → win scenarios)
- Test edge cases and error states
- Evaluate mobile responsiveness and touch interactions
- Assess accessibility features
4. Analyze Engagement Factors
- Evaluate core concept and value proposition
- Assess visual design and user interface polish
- Analyze content quality and variety
- Identify social or multiplayer aspects
- Check for replayability and progression systems
5. Provide Structured Feedback
- Rate overall experience on key metrics (fun, usability, polish)
- Categorize findings: Strengths, Critical Issues, Minor Issues
- Provide specific, actionable recommendations
- Suggest priority improvements for maximum impact
Quality Criteria
Comprehensive Coverage: Test all major features and user paths Critical Perspective: Focus on user experience gaps, not just technical excellence Actionable Feedback: Provide specific recommendations with rationale Balanced Assessment: Include both positives and areas for improvement User-Centric Focus: Evaluate from end-user perspective, not developer viewpoint
Assets
Feedback Template
## Overall Rating: X/10
### Strengths
- [List key positives]
### Critical Issues
- [List major problems impacting user experience]
### Minor Issues
- [List small UX improvements]
### Recommendations
- [Specific, actionable suggestions with priority]
Example Evaluation
## Overall Fun Factor: 6/10
### Strengths
✅ Simple & Intuitive: Core mechanic immediately understandable
✅ Visual Polish: Clean design with good color feedback
✅ Mobile-First: Responsive design works well on touch devices
### Critical Issues
❌ Limited Replayability: No goals after first bingo
❌ Question Imbalance: Some too common, some too rare
❌ Social Features Missing: No group play support
### Minor Issues
- Back button confusing (resets progress)
- No undo for accidental taps
- Missing sound/haptic feedback
### Recommendations
1. Add progressive goals (blackout bingo, scoring)
2. Expand question pool with balanced difficulty
3. Implement multiplayer features for group play
Tool Integration
Automatic Checks
- runTests: Verify unit tests pass before user testing
- run_in_terminal: Build app and launch dev server
- read_file: Explore codebase structure and key components
- semantic_search: Find relevant code patterns and features
Optional Enhancements
- runSubagent: For deep codebase exploration if needed
- vscode_askQuestions: Clarify testing focus or user personas
- $BROWSER: Open app in browser for visual inspection
Common Scenarios
Game Apps: Focus on engagement, replayability, and progression systems
Productivity Tools: Emphasize usability, efficiency, and workflow optimization
Social Apps: Prioritize interaction design and community features
Mobile-First Apps: Test touch interactions, responsiveness, and offline capabilities
When not to use it
- →Automated regression testing
Prerequisites
Limitations
- →Requires manual user-perspective simulation
How it compares
It provides a qualitative, user-centric evaluation rather than a purely technical or functional test report.
Compared to similar skills
dogfooding side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dogfooding (this skill) | 0 | 3mo | No flags | Intermediate |
| ux-audit | 0 | 4mo | Review | Advanced |
| dogfooding | 0 | 2mo | No flags | Intermediate |
| qa | 0 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
ux-audit
rioX432
Comprehensive UI/UX audit: heuristic evaluation, accessibility, visual analysis, platform guidelines, and improvement proposals — then create GitHub Issues
dogfooding
litago75
Critically dogfood the running app by playing real user flows and reporting severity-ranked UX and fun feedback with concrete code-linked fixes. Use when asked to test the app experience, evaluate engagement, or provide product-quality UX critique.
qa
heliohq
>
roast
diegosouzapw
Multi-perspective UI/UX roasting workflow with iterative improvement cycles
naive-ux-check
ByronWilliamsCPA
Surface the next unrun Claude-for-Chrome naive-user comprehension prompt (kid, guardian, or admin persona), and log the pasted-back response to a dated findings report. Use before a release, or whenever you want a fresh naive-user pass over the app.
sb-ux-product-audit
HideakiSolutions
Audite frontend como produto real vs MVP incompleto vs scaffold, com gaps UX, tecnicos e testes ausentes.