DO

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.zip

Installs 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.
248 chars✓ has a “when” trigger
Intermediate

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

You give it
An optional focus area (fun, onboarding, retention, accessibility)
You get back
A dogfooder verdict, severity-ordered findings with code links, what is working well, and top improvements

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

  1. Ensure app is running locally.
  2. Play at least one full primary loop.
    • Start screen -> in-game interactions -> win state or terminal state -> replay/reset path.
  3. Stress key interactions.
    • Fast-path completion (speed-run behavior).
    • Error/edge behavior (toggle, undo, reset, back navigation).
    • Post-win continuation behavior and replay quality.
  4. Capture concrete evidence.
    • Cite exact UI behavior observed in browser interactions.
    • Map major findings to code locations when possible.
  5. Report findings in severity order.
    • Focus on bugs, UX friction, fun blockers, retention risks.
    • Keep summaries brief after findings.
  6. Provide actionable fixes.
    • Propose high-leverage changes first.
    • Include smallest effective next steps.

Report Format

  1. Dogfooder verdict (short score + rationale).
  2. Findings ordered by severity.
    • Severity level.
    • Observed behavior.
    • User impact (fun/usability).
    • Relevant file links when available.
  3. What is working well.
  4. Highest-leverage improvements (top 3-5).

Workspace Anchors

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.

SkillInstallsUpdatedSafetyDifficulty
dogfooding (this skill)02moNo flagsIntermediate
ui-ux-expert-skill919moReviewAdvanced
react-best-practices223moNo flagsIntermediate
frontend-testing113moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry