Loading...
Loading...
Found 9 Skills
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y. Use for Playwright/Cypress/Vitest/Jest/RTL, flaky test triage, CI stabilization, and canvas/WebGL games (Phaser) needing deterministic input + screenshot/state assertions.
The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria, and iterate until it passes with before/after proof.
Evidence-based Quality Verification for Games. Launch the actual build on the selected target runtime to prove real rendering, input, core loop, at least one designed outcome, restart functionality, and explicit limitations, without framing subjective fun as a definitive verdict. This method is used for testing generated games, conducting QA on game builds, checking whether a game is fully playable, or verifying builds.
Pre-publish verification gauntlet for Roblox games
Define creation, naming, and replacement rules for placeholder assets so the game is testable before final art exists.
Create, improve, debug and package playable 2D games in Go with Ebitengine (github.com/hajimehoshi/ebiten/v2). Use for Ebitengine game requests: game design translated into a complete loop, input, rendering, text, audio, scenes, gameplay tests and desktop, browser or mobile builds. Also use when fixing these systems in an existing Ebitengine game. Do not apply to unrelated Go software or engine-internal patches merely because they depend on Ebitengine.
Use Roblox Studio MCP safely and productively from Claude. Use when connecting to Studio, inspecting a Roblox place, editing scripts or instances, inserting assets, generating models/materials, or playtesting through MCP tools.
Use when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering input prompts, going back, and reading/writing storage — via `Game.testing`, the opt-in devtools bridge exposed on `window`. Load this before wiring up automated/agent-driven playtesting, not for authoring story content itself (see `pixi-vn-narration`).