game-quality
Skill27 starsChanged 2 months agoMITView on GitHub
Pushing a game from "runs" to "good" - concept viability, finding the missing decision when it plays flat, and disproving "this is fun" with playtest evidence. Optional aids, not gates.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sebnado/worldbuild-benchtheir own version, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- sebnado/worldbuild-bench★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- craftSkill
- game-architectureSkill
- game-audioSkill
- game-axiomsSkill
- game-feelSkill
- game-mechanicsSkill
- game-narrativeSkill
- game-onboardingSkill
- game-playbooksSkill
- gameSkill
- objectSkill
- skillsSkill
- threeSkill
- worldSkill
The file
Files
quality/ — production quality
Reference for pushing a game from "runs" to "good." These are optional aids, not gates — pull the one that matches the problem in front of you:
market-reality.md— when choosing a concept or deciding whether the fantasy has a real audience.fun-compiler.md— when the game runs but plays flat and you need to find the missing decision.skills/craft/performance.md— when choosing renderer, lights, postFX, particles, instancing, or assets.playtest-protocol.md— when you want to disprove "this is fun" with evidence instead of hope.
What "good" means here
Two things, equal weight: it looks alive and it plays well. Useful questions to interrogate either one:
- Audience pull: who clicks the first screenshot, and why now?
- Aesthetic target: what feeling should the player get?
- Dynamics → Mechanics: what repeated behavior creates that feeling, and what exact rules produce it?
- Visual contract: what Three.js recipe keeps play readable inside budget?
- Proof loop: what playtest evidence shows it's fun, not just pretty?
The real check
There is no audit script. The check is your eyes and your hands: node harness/capture.mjs <world>
and look at the frame, then play it. Fix the single worst thing, capture again,
repeat until it looks alive and plays well. That loop catches everything a
keyword audit never could.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.