By tykisgod
Orchestrate agent-driven game development workflows in Unity using 26 slash commands for lifecycle routing: decompose visions into executable epics, generate/review C# code and design docs, author/run EditMode/PlayMode tests, enforce git worktree isolation, auto-compile/verify changes, and produce Mermaid diagrams with PR checklists.
npx claudepluginhub tykisgod/quick-questionAuthor Unity EditMode, PlayMode, or regression tests for the current change without conflating that with test execution.
Quick Unity best-practice check — run after editing C# files to catch anti-patterns, performance issues, and runtime safety problems.
Decompose a high-level game vision (pillars + rules + references) into executable epics, then orchestrate the full qq pipeline for each. Use when starting a new project, bootstrapping a prototype from a pitch, or breaking a large initiative into parallel workstreams.
Compare the current branch against develop and generate two review documents: architecture change diagram + PR review checklist.
Summarize all changes Claude Code made during this conversation.
Deep code review via Claude subagent — reviews uncommitted changes by default, loops until no critical issues remain. Use after /qq:test passes, before /qq:commit-push.
Send a design document to a Claude subagent for review, then revise the document based on findings. Automatically loops until no critical issues remain or 5 rounds are complete.
Cross-model code review via Codex CLI — reviews uncommitted changes by default, loops until no critical issues remain. Use after /qq:test passes, before /qq:commit-push.
Send a design document to Codex CLI for review, then revise the document based on the findings. Automatically loops until no critical issues remain or 5 rounds are completed.
Batch commit all uncommitted changes and push to the remote repository.
Analyze .asmdef dependency relationships — Mermaid graph + dependency matrix + issue detection.
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.
Write a game design document from a one-liner, rough draft, or feature discussion. Outputs a structured design doc ready for /qq:plan. Use when starting a new feature, fleshing out a game idea, or documenting a design before implementation.
Compare design documents against actual code/config, find inconsistencies, and output a prioritized attention list.
Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.
Smart implementation — read a plan, execute step by step with auto-compilation, subagent dispatch for large tasks, and checkpoint-based resume.
Explain the architecture and logic of a specified module or design in plain, approachable language.
Composite command: run /qq:brief and /qq:timeline in parallel, generating a complete PR review package.
Entry point — detect where you are in the dev workflow and guide you to the right next step.
Explain technical concepts using everyday analogies that a grandma or 5-year-old could understand.
Generate a technical implementation plan from a game design document or a brief description. Outputs architecture, interfaces, ordered steps with file paths.
Review a game design document from an implementer's perspective — check self-consistency, playability, buildability, and codebase gaps. Use after writing a design doc, or when you want to validate an existing design against the current codebase.
Review changes from the most recent interaction (skills, configs, settings, and other lightweight changes) for quality and consistency.
Search GitHub, Stack Overflow, and technical blogs for solutions to a technical implementation problem. Returns a comparative analysis with a recommendation. Use when facing a technical decision, choosing a library, or looking for proven patterns in similar projects.
Run Unity unit/integration tests and check for runtime errors.
Group the current branch's commit history into semantic phases along a timeline, and generate two review documents: architecture evolution + code review.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimCommands for game development workflows
Game development engineering agents providing expertise in engine architecture, gameplay systems, and performance optimization
A game development scaffold for Claude Code with layered rules, specialized agents, reusable skills, workflow commands, contexts, hooks, and engine-isolated packs for Unity, Unreal, and Godot.
Comprehensive game development learning system with 7 specialized agents, 21 in-depth skills, 4 slash commands, and automation hooks. Master game design, programming, graphics, audio, networking, tools, and publishing across Unity, Unreal Engine, and Godot.
AI workflow system for game development
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
The control plane for game-dev agents.
Close the loop — compile, test, review, and ship — across Unity, Godot, Unreal, and S&box.
Claude Code-first.
Open to any agent via HTTP and MCP.
|
Unity |
Godot |
Unreal |
S&box |
✅ Verified path: Claude Code + Unity 2021.3+ on macOS or Windows. Daily-driven, end-to-end battle-tested. This is the recommended setup if you want everything in this README to "just work".
🧪 Experimental — contributions welcome: Godot, Unreal, and S&box adapters ship as scaffolds. The bridge code, command surface, and CI smoke tests are in place, but no one has yet shipped a real game using any non-Unity adapter — they have not been validated in actual development use. Same caveat for non-Claude hosts (Codex CLI, Cursor, Continue, other MCP hosts): the runtime is agent-agnostic by design, but the verified loop is Claude Code-only. If you're building with one of these, your bug reports and PRs are how the adapter graduates to "verified" — see CONTRIBUTING.md.
AI agents can write code. They cannot, by default, tell you whether the code compiles, the tests pass, the behavior is right, or whether they just produced 500 lines of plausible-looking nonsense. In a game project — where "running" means the editor opens, the scene loads, and frame N+1 looks like you wanted — that gap is the entire problem.
quick-question is the runtime layer that closes it. Four work modes — prototype, feature, fix, hardening — are first-class state, not flavor text. A prototype keeps the compile green and stays playable; a hardening pass forces tests, review, and document/code consistency before shipping. The artifact-driven controller (/qq:go) reads .qq/state/*.json and your work_mode, then recommends the concrete next skill — instead of guessing from chat history.
The runtime is engine-symmetric and agent-agnostic. tykit gives Unity the deepest integration (an in-process HTTP server, millisecond response). Godot, Unreal, and S&box are at runtime parity through Python bridges. Claude Code gets 26 skills, auto-compile hooks, and review gates. Codex, Cursor, Continue, and any MCP-compatible host get the same underlying runtime through HTTP and MCP. Structured state in .qq/ is plain JSON on disk — readable by any agent, across sessions.
The methodology is grounded in the document-first approach described in AI Coding in Practice: An Indie Developer's Document-First Approach.
Edit .cs/.gd/.cpp file
→ Hook auto-compiles via qq-compile.sh
→ Result + error context written to .qq/state/
→ /qq:go reads state, recommends next skill
→ Skill runs, writes new state
→ Loop
Four layers cooperate: