Design research
The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity, Godot, Unreal, and S&box. Lifecycle-aware /qq:go routing, 26 /qq:* slash commands. Claude Code-first, agent-agnostic via HTTP and MCP.
npx -y skills add tykisgod/quick-question --skill design-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Search for how other games solve a specific design problem — game loops, mechanics, systems, progression, economy. Returns a comparison of 2-4 reference games with what to borrow. Use when designing a new feature, exploring game mechanics, or looking for design inspiration before writing a design doc.
SKILL.md
1.7 KB, as published. Nobody here has run it
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Search for game design references to the problem currently being discussed. Focus on design patterns and player experience, not code.
Arguments: $ARGUMENTS
Process
- Identify the core design question (e.g., "how to structure a survival loop on a ship", "how trading between cities creates interesting choices")
- Search for game design analyses, GDC talks, postmortems, and design breakdowns using WebSearch. Good query patterns:
"[game name]" game design analysis [mechanic]GDC [mechanic] design postmortem[mechanic] game design breakdown
- Organize into a comparison table:
| Game | How they do it | What makes it fun | What we could borrow |
|---|
- Recommend which approach best fits this project's scope and feel, and why
Notes
- Focus on the player experience, not implementation — "RimWorld uses a bill queue per workbench that lets players set min/max thresholds" is good; "WorkGiver_DoBill class" is not
- Prefer games the team has likely played or that are well-documented
- Include at least one game from a different genre if it solves the same design problem in an interesting way
- If searching yields thin results, lean on your own knowledge of game design — but flag which insights came from search vs. your own analysis