dogfooding
A hands-on review tool for evaluating app user flows, fun factor, and usability with concrete, code-linked fixes.
Install
mkdir -p .claude/skills/dogfooding-litago75 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15078" && unzip -o skill.zip -d .claude/skills/dogfooding-litago75 && rm skill.zipInstalls to .claude/skills/dogfooding-litago75
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.
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.Key capabilities
- →Play at least one full primary app loop
- →Stress key interactions like fast-path completion and error handling
- →Capture concrete evidence of UI behavior
- →Map major findings to code locations
- →Report findings ordered by severity
- →Provide actionable fixes with high-use changes
How it works
The skill involves hands-on interaction with a running local application, playing through primary loops and stressing key interactions. It captures observed UI behavior, maps findings to code, and reports them by severity with proposed fixes.
Inputs & outputs
When to use dogfooding
- →Evaluating app onboarding UX
- →Testing user flow for fun and engagement
- →Identifying UI friction points
About this skill
Dogfooding Skill
Hands-on product review workflow for this workspace. Prefer direct interaction over code-only analysis.
When To Use
- User asks to dogfood, playtest, or critically review UX.
- User asks if the app is fun, engaging, sticky, or clear.
- User wants feedback tied to actual interaction evidence.
Inputs
- Optional focus area: fun, onboarding, retention, accessibility.
- If no focus is provided, default to fun + usability.
Procedure
- Ensure app is running locally.
- Start with npm run dev if needed.
- Open browser at http://localhost:5173/.
- Play at least one full primary loop.
- Start screen -> in-game interactions -> win state or terminal state -> replay/reset path.
- Stress key interactions.
- Fast-path completion (speed-run behavior).
- Error/edge behavior (toggle, undo, reset, back navigation).
- Post-win continuation behavior and replay quality.
- Capture concrete evidence.
- Cite exact UI behavior observed in browser interactions.
- Map major findings to code locations when possible.
- Report findings in severity order.
- Focus on bugs, UX friction, fun blockers, retention risks.
- Keep summaries brief after findings.
- Provide actionable fixes.
- Propose high-leverage changes first.
- Include smallest effective next steps.
Report Format
- Dogfooder verdict (short score + rationale).
- Findings ordered by severity.
- Severity level.
- Observed behavior.
- User impact (fun/usability).
- Relevant file links when available.
- What is working well.
- Highest-leverage improvements (top 3-5).
Workspace Anchors
- App shell: src/App.tsx
- Game state and persistence: src/hooks/useBingoGame.ts
- Rules engine: src/utils/bingoLogic.ts
- In-game UI: src/components/GameScreen.tsx
- Win modal: src/components/BingoModal.tsx
Quality Bar
- Do not provide feedback without interaction evidence.
- Do not stop at generic advice; tie feedback to observed behaviors.
- Prioritize issues that reduce fun, clarity, or replay value.
- Explicitly call out if a critical loop is too easy to game or lacks reward.
When not to use it
- →When the app is not running locally
- →When feedback is required without interaction evidence
- →When generic advice is sufficient without tying it to observed behaviors
Limitations
- →Requires the app to be running locally.
- →Feedback must be supported by interaction evidence.
- →Prioritizes issues that reduce fun, clarity, or replay value.
How it compares
This skill provides a structured, interactive product review by simulating real user flows and linking observed UX issues directly to code, offering more concrete and actionable feedback than a code-only analysis.
Compared to similar skills
dogfooding side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dogfooding (this skill) | 0 | 2mo | No flags | Intermediate |
| ui-ux-expert-skill | 91 | 9mo | Review | Advanced |
| react-best-practices | 22 | 3mo | No flags | Intermediate |
| frontend-testing | 11 | 3mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
ui-ux-expert-skill
fercracix33
Technical workflow for implementing accessible React user interfaces with shadcn/ui, Tailwind CSS, and TanStack Query. Includes 6-phase process with mandatory Style Guide compliance, Context7 best practices consultation, Chrome DevTools validation, and WCAG 2.1 AA accessibility standards. Use after Test Agent, Implementer, and Supabase agents complete their work.
react-best-practices
redpanda-data
Client-side React performance optimization patterns.
frontend-testing
langgenius
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
flow
Use when you need to run Flow type checking, or when seeing Flow type errors in React code.