By dawn840705
Full game development studio for Claude Code: 34 specialist agents, 72 workflow skills, and production hooks covering pre-production through live-ops. v0.3.0 adds Unity UI/UX guidelines (5 permanent rules + UIAutoSelectGuardian.cs helper), Unity MCP workflow patterns, scene-loading anti-patterns, and subagent parallel collaboration rules.
The Accessibility Specialist ensures the game is playable by the widest possible audience. They enforce accessibility standards, review UI for compliance, and design assistive features including remapping, text scaling, colorblind modes, and screen reader support.
The AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation, pathfinding optimization, enemy behavior programming, or AI debugging.
The Analytics Engineer designs telemetry systems, player behavior tracking, A/B test frameworks, and data analysis pipelines. Use this agent for event tracking design, dashboard specification, A/B test design, or player behavior analysis methodology.
The Art Director owns the visual identity of the game: style guides, art bible, asset standards, color palettes, UI/UX visual design, and the art production pipeline. Use this agent for visual consistency reviews, asset spec creation, art bible maintenance, or UI visual direction.
The Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound palette definition, music cue planning, or audio system architecture.
Brownfield onboarding — audits existing project artifacts for template format compliance (not just existence), classifies gaps by impact, and produces a numbered migration plan. Run this when joining an in-progress project or upgrading from an older template version. Distinct from /project-stage-detect (which checks what exists) — this checks whether what exists will actually work with the template's skills.
Pre-flight cost approval gate for any paid AI API call (image / 3D / audio / video / text generation services). Forces explicit 4-point disclosure (call type / cost estimate / purpose / use) before invocation. Use before any Suno/ElevenLabs/Midjourney/OpenAI/Tripo/etc. paid call. Use when user says 'check cost first', 'cost gate', 'approve API call'.
Creates an Architecture Decision Record (ADR) documenting a significant technical decision, its context, alternatives considered, and consequences. Every major technical choice should have an ADR.
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.
Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset production. Run after /brainstorm is approved and before /map-systems or any GDD authoring begins.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Claude Code 플러그인 형태로 패키징된 완전한 게임 개발 스튜디오.
전문 에이전트 34종 · 워크플로우 skill 76종 · production hooks · 거버넌스/워크플로우 자산 (v0.2.0+) — 프리프로덕션 → 프로덕션 → QA → 릴리스 → 라이브 옵스 전 단계 커버.
실제 게임 스튜디오 구조를 그대로 모사: 디렉터(creative / technical / producer)가 부서장(design / programming / art / audio / narrative / QA)을 조율하고, 부서장이 다시 스페셜리스트(gameplay programmer / level designer / economy designer 등)를 조율합니다. 모든 디자인 에이전트와 템플릿은 검증된 게임 디자인 이론(MDA, Self-Determination Theory, Flow State, Bartle Player Types)에 기반합니다.
엔진 무관(Engine-agnostic). Godot, Unity, Unreal, GameMaker, 또는 커스텀 엔진 모두에서 동작합니다.
디렉터 · 부서장 · 스페셜리스트 — 실제 게임 스튜디오 조직도 그대로:
creative-director, technical-director, producergame-designer, systems-designer, economy-designer, level-designer, narrative-director, world-builder, writer, live-ops-designerlead-programmer, gameplay-programmer, ui-programmer, ai-programmer, engine-programmer, network-programmer, tools-programmer, prototyperart-director, technical-artist, audio-director, sound-designerqa-lead, qa-tester, performance-analyst, security-engineer, accessibility-specialist, localization-lead, release-manager, devops-engineerux-designer, community-manager, analytics-engineer개발 단계별로 정리:
/start, /brainstorm, /map-systems, /design-system, /review-all-gdds, /consistency-check, /create-architecture, /architecture-decision, /architecture-review, /create-control-manifest, /art-bible, /ux-design, /ux-review, /setup-engine, /adopt, /gate-check/create-epics, /create-stories, /story-readiness, /dev-story, /story-done, /quick-design, /sprint-plan, /sprint-status, /scope-check, /estimate, /propagate-design-change, /reverse-document, /asset-spec, /asset-audit/code-review, /tech-debt, /design-review/qa-plan, /test-setup, /test-helpers, /test-evidence-review, /test-flakiness, /regression-suite, /smoke-check, /soak-test, /bug-report, /bug-triage, /balance-check, /playtest-report, /content-audit/team-audio, /team-combat, /team-level, /team-live-ops, /team-narrative, /team-polish, /team-qa, /team-release, /team-ui/release-checklist, /launch-checklist, /day-one-patch, /hotfix, /patch-notes, /changelog, /milestone-review, /retrospective, /security-audit, /perf-profile, /localize, /onboard, /project-stage-detect, /help, /prototype, /skill-test, /skill-improve/sot-audit (다중 source-of-truth 정합성 감사), /legacy-purge (피봇/마이그레이션 잔재 청소)/governance-bible-init (사운드/아트/내러티브 등 도메인 Bible 부트스트랩), /api-cost-gate (유료 AI API 호출 전 4건 명시 승인 게이트)SessionStart: 프로젝트 컨텍스트 로드 + 누락 문서 감지PreToolUse (Bash): git 커밋/푸시 검증 (한국어 컨벤션 기본 — 프로젝트별 오버라이드 가능)PostToolUse (Write/Edit): 자산 명명 검증, skill 파일 변경 감지, Unity 전용 안전장치 (자동 opt-in, v0.2.0+)Notification/PreCompact/PostCompact/Stop: 컨텍스트 압축 및 세션 로깅SubagentStart/Stop: 에이전트 활동 로깅플러그인이 Unity 프로젝트(Assets/ + ProjectSettings/ 존재)를 자동 감지하면 두 advisory hook 이 활성화됩니다:
unity-meta-check.sh — .cs/.shader/.prefab 등을 짝 .meta 없이 작성한 경우 경고 (다른 머신에서 GUID 깨짐 방지)unity-animator-string-lint.sh — Animator.SetBool("name", ...) 같은 문자열 lookup 패턴 감지 시 경고 (StringToHash 캐싱 권고)추가로 수동 opt-in git pre-commit 템플릿(templates/githooks/unity-pre-commit)이 있어 .meta 누락 커밋을 차단. 활성화는 docs/engine/unity-setup.md 참고.
비-Unity 프로젝트에서는 모두 즉시 종료(silent exit) — 영향 없음.
엔진/장르/플랫폼 무관하게 적용되는 워크플로우 자산:
| 자산 | 위치 | 용도 |
|---|---|---|
| 회의록 템플릿 | docs/templates/meeting-template.md | 헤더 메타박스 + D-table 결정 + 메모리화 프로토콜 |
| API CLI 템플릿 | docs/templates/api-cli-template.py | pay-as-you-go 외부 AI API wrapper 스캐폴드 (env 로드 / 인증 / 비동기 폴링 / 동기 binary / 다운로드) |
| 토큰 효율 룰 | docs/rules/token-efficiency.md | R1 |
| 자산 정리 룰 | docs/rules/artifact-organization.md | 3-zone 규율 (Workshop / Curated / Engine) + prefix 명명 규칙 + .prompt.txt 동반 룰 |
# Claude Code 안에서:
/plugin marketplace add dawn840705/claude-code-game-studios
/plugin install claude-code-game-studios@game-studios
이미 0.1.0 이 설치되어 있는 프로젝트는 업데이트만:
npx claudepluginhub dawn840705/claude-code-game-studios --plugin claude-code-game-studiosDevelop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.