Donchitos/Claude-Code-Game-Studios

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

About the project

Claude Code Game Studios is a setup that organizes Claude Code into a coordinated game-development team of specialized AI agents. It supports game projects across design, programming, art, audio, narrative, quality assurance, and production, with skills and workflows for coordinating that work.

This repository also configures its own agents. See what Claude-Code-Game-Studios tells them →

27kStars on the repository
134Mods indexed here, across every type
9d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

skill-test

49

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Validate skill files for structural compliance and behavioral correctness. Four modes: static linter, spec, category rubric, audit.

not rated 27k +625 changed 8d ago A SkillSpector: warn 27 tokens original MIT

smoke-check

50

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.

not rated 27k +625 changed 8d ago A SkillSpector: warn 29 tokens original MIT

soak-test

51

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.

not rated 27k +625 changed 8d ago A SkillSpector: warn 30 tokens original MIT

sprint-plan

52

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

New or updated sprint plan from the current milestone, completed work, and available capacity.

not rated 27k +625 changed 8d ago A SkillSpector: warn 21 tokens original MIT

sprint-status

53

Donchitos/Claude-Code-Game-Studios

Skill Claude Code needs its repo

Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'.

not rated 27k +625 changed 17d ago A SkillSpector: warn 28 tokens original MIT

start

54

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

First-time onboarding — asks where you are, then guides you to the right workflow.

not rated 27k +625 changed 8d ago B SkillSpector: warn 19 tokens original MIT

story-done

55

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

End-of-story completion review — verifies each acceptance criterion, checks GDD/ADR deviations, prompts code review, updates status.

not rated 27k +625 changed 8d ago A SkillSpector: warn 29 tokens original MIT

story-readiness

56

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

not rated 27k +625 changed 8d ago A SkillSpector: warn 35 tokens original MIT

team-audio

57

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the audio team — audio-director, sound-designer, technical-artist, gameplay-programmer — direction through implementation.

not rated 27k +625 changed 8d ago A SkillSpector: warn 31 tokens original MIT

team-combat

58

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the combat team — game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester — design through implement and validate.

not rated 27k +625 changed 8d ago A SkillSpector: warn 41 tokens original MIT

team-level

59

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the level team — level-designer, narrative-director, world-builder, art-director, systems-designer, qa-tester — for complete area creation.

not rated 27k +625 changed 8d ago A SkillSpector: warn 38 tokens original MIT

team-live-ops

60

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.

not rated 27k +625 changed 8d ago A SkillSpector: warn 40 tokens original MIT

team-narrative

61

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.

not rated 27k +625 changed 8d ago A Socket: passSnyk: passSkillSpector: warn 35 tokens original MIT

team-polish

62

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.

not rated 27k +625 changed 8d ago A SkillSpector: warn 38 tokens original MIT

team-qa

63

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.

not rated 27k +625 changed 8d ago A SkillSpector: warn 35 tokens original MIT

team-release

64

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

not rated 27k +625 changed 8d ago A SkillSpector: warn 33 tokens original MIT

team-ui

65

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Orchestrate the UI team through the UX pipeline — authoring, visual design, implementation, review, polish. Uses /ux-design, /ux-review, studio templates.

not rated 27k +625 changed 8d ago A SkillSpector: warn 38 tokens original MIT

tech-debt

66

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

not rated 27k +625 changed 8d ago A SkillSpector: warn 25 tokens original MIT

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.

not rated 27k +625 changed 17d ago A SkillSpector: warn 38 tokens original MIT

test-flakiness

68

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.

not rated 27k +625 changed 17d ago A SkillSpector: warn 27 tokens original MIT

test-helpers

69

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Generate engine-specific test helper libraries — assertion utilities, factory functions, mocks in the engine's test folder. Reduces boilerplate.

not rated 27k +625 changed 17d ago A SkillSpector: warn 30 tokens original MIT

test-setup

70

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.

not rated 27k +625 changed 8d ago A SkillSpector: warn 32 tokens original MIT

ux-design

71

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Section-by-section UX spec authoring for a screen, flow or HUD. Reads the player journey to provide context; also project-wide accessibility.

not rated 27k +625 changed 8d ago A SkillSpector: warn 31 tokens original MIT

ux-review

72

Donchitos/Claude-Code-Game-Studios

Skill Claude Code

Validate a UX spec, HUD design or pattern library — accessibility, GDD alignment, readiness. APPROVED / NOT ASSESSED / NEEDS REVISION / MAJOR REVISION NEEDED.

not rated 27k +625 changed 8d ago A SkillSpector: warn 42 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: