Skip to content
Get packs

Test Playable Web Games

Lets an agent QA browser games with deterministic fixtures, real playthroughs and browser evidence.

Source Download skill
Repository
MengTo/Skills
Stars
7,187
Licence
MIT
Files
2 files

What it does

When installed, the agent follows a structured QA process for browser-based games: it maps the player journey (launch, controls, core actions, save/continue, retry, settings), jumps directly to specific game states using seedable fixtures or debug URLs instead of grinding through play, and checks that the screen actually responds to each action. It also checks the console for errors, samples performance on a live scene, and writes up reproducible bug reports separating new regressions from old issues.

Great for

  • Indie or small teams shipping a browser game who want a repeatable pre-release checklist
  • Developers who need reproducible bug reports with device, viewport and steps to reproduce
  • QA testers covering desktop, touch, mobile and reduced-motion variants of a web game

Skip it if

  • Native console or desktop game testing, since the skill is scoped to playable web games in a browser
  • Projects with no deterministic test hooks or debug routes, where much of the guidance cannot be applied without building them first
  • Teams expecting automated certification of fun or balance; the skill checks behaviour and evidence, not design quality

Try asking

  • “Test our playable web game end to end on desktop and mobile, including save and continue flows.”
  • “Run a regression pass on the combat and inventory screens using debug states instead of full playthroughs.”
  • “Check the console for errors and do a quick performance smoke test on the main level.”
  • “Write up the bugs you find with reproduction steps, severity and viewport details.”
Step-by-step guide: how to use Test Playable Web GamesInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    test-playable-web-games.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip test-playable-web-games.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip test-playable-web-games.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Expose debug routes or query parameters for key game states before asking for testing, so the agent can reach them directly.
  • Name the repository's approved browser tool and any local restrictions in your request so the agent honours them.
  • Ask for a baseline run first so new regressions can be separated from existing issues.

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from MengTo/Skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.