msu-skillsClaude Code
The marketplace only has to be added once.
/plugin install game-tools@msu-skillsPlugin
game-tools
Quality checks and fixes for a game that already runs, on any engine or platform. It covers the parts of a game that are not features: how the controls feel, whether the numbers are balanced, whether the same input always gives the same result, whether the UI fits every screen and input device, whether the sound plays on every browser and phone, whether a new player understands what to do, and whether the text works in other languages. It also ships an in-game panel for changing values while playing, instead of another edit-and-rebuild round. Published by NEXPACE alongside the MSU builder skills.
Install
Pick a channel
skills CLI
No plugin boundary on this channel — every catalogued skill is offered. --skill picks one.
npx skills add NEXPACE-Limited/msu-skillsCodex · Gemini · Kimi
Piped from main. Review the script first if you would rather not pipe a remote one into Bash.
curl -fsSL https://raw.githubusercontent.com/NEXPACE-Limited/msu-skills/main/install.sh | bash -s -- --plugin game-toolsSkills · 8
What each one does
Checks, repairs, or sets up a browser game's audio: its sound settings and whether sound actually plays under each browser's conditions.
Read the rest
Use when a game is silent, or goes silent, on a phone, in Safari, inside an iframe or an in-app browser while it plays elsewhere; when sound works for the builder but not for players; when music does not start, loops with a gap, or keeps playing in a hidden tab; when volume, mute, or sound settings are missing, ignored on some device, or forgotten between sessions; when the user asks to add sound or music to a game; or when a pre-release audio pass is requested. Reports observed versus inferred findings and applies fixes only on confirmation.
Reviews and tunes game balance across difficulty and progression curves, session pacing, option or strategy trade-offs, and reward economies.
Read the rest
Use when players report that a game is too hard, easy, short, long, or grindy; a weapon, upgrade, or strategy dominates; damage, health, spawn, drop, price, or progression values need tuning; or a requested pre-release balance pass has not been validated. Establishes the target experience, measures the relevant model, and reports or applies specific number changes with before-and-after evidence.
Audits a game's UI and interaction across supported viewports, aspect ratios, pixel densities, orientations, and input capabilities.
Read the rest
Use when mobile, tablet, desktop, controller, keyboard, pointer, or touch support is being checked; UI clips, overlaps, blurs, or overflows; controls are unreachable or hard to use; resizing or orientation changes break layout; or an explicit pre-release device-coverage pass is requested. Reproduces each issue on the relevant target and reports severity, evidence, exact trigger conditions, and fixes while distinguishing observed from source-inferred findings.
Use when creating any game or interactive toy, when adding gameplay/UI features to one, when the builder asks for value tweaks in any language (too fast/slow, too big/small, a bit more/less, move it left/right/up/down, can't hit it, my tap doesn't register, hitbox, feels floaty/heavy/off, easier/harder, change X from N to M, 'don't rebuild — just fix this'; 너무 빨라요/느려요, 버튼이 안 눌려요, 판정이 이상해요, 히트박스, 이것만 고쳐줘), or when a message contains a [TUNING] or [ERRORS] block.
Read the rest
Once loaded, stays in force for every subsequent message in the session without being re-mentioned. Ships a live in-game tuning panel with every game so builders adjust values themselves instead of burning chat round-trips.
Audits nondeterministic game behavior and flaky execution.
Read the rest
Use when the same initial state and inputs produce different outcomes, a test fails intermittently or only under load, behavior differs by frame rate or machine, a replay diverges, or lockstep peers desynchronize. Establishes the required determinism boundary, reproduces and measures variance, isolates randomness, timing, async or thread ordering, state leakage, unordered iteration, and numeric drift, then reports verified causes and implements and stress-tests fixes only when requested.
Use when a game's controls feel stiff, floaty, heavy, slippery, unresponsive, or unfair; when players miss jumps they thought they made, snag on platform corners, lose inputs pressed during another action, or get hit by grazes; when a platformer, runner, or action game is being built or polished and its input and movement handling was never reviewed; or when the user asks for a game-feel pass or names coyote time, jump buffering, variable jump height, gravity tuning, corner correction, acceleration, or input buffering.
Read the rest
Audits, proposes, and applies only what the user confirms.
Audits, adds, or reworks a game's first-time-player tutorial.
Read the rest
Use when players cannot identify the controls, goal, failure conditions, or a non-obvious rule; new players quit before completing the core loop; onboarding presents too much at once; or an explicit tutorial or first-run improvement is requested. Separates first-action essentials from later guidance, prefers in-flow or staged first-run teaching, provides a skippable fallback and reusable help, and verifies behavior from clean, completed, and skipped states.
Sets up or repairs localization for a game: player-facing string extraction, locale catalogs, draft target-locale translations, fallback and locale selection, runtime switching, plural and parameter formatting, glyph coverage, and translation-safe layouts.
Read the rest
Use when the user requests another locale or localization-ready architecture; existing translations, fallback, pluralization, locale detection, or switching are broken; or translated text overflows or renders missing glyphs. Follows the project's engine and existing localization system and marks generated translations for human review.