review-game — Claude Code skill: audit a game codebase
Audits an existing game project for architecture, performance, code quality and monetization readiness. Read-only, no edits.
npx skills add PlayableIntelligence/game-creator --skill review-game -a claude-codeWhat review-game does
The skill inspects a game project and returns a scored report across four areas. It starts by detecting the engine (Three.js, Phaser or another), reading package.json, the entry point and index.html, then works through the checklists.
Architecture: is there an EventBus, a single GameState, centralized constants, an orchestrator, core/systems/gameplay/ui/level layers. Performance: is getDelta() capped, are temp objects pooled, are Three.js geometries and materials disposed, are listeners cleaned up on scene transitions. Then code quality and monetization readiness — a points system, session tracking, a structure that could support server-side score validation.
You get scores per section, a prioritized list of recommendations in plain language, and a section on what already works. Nothing in the codebase is changed: this is analysis, and improve-game handles the fixes. Pass the project path as an argument, or it falls back to the current directory.
What it helps with
- understand an unfamiliar game project before extending it
- spot memory leaks from undisposed Three.js resources
- check whether event listeners pile up across scene transitions
- assess if the scoring system can support server-side validation
- get a prioritized fix list instead of generic advice
Example prompts for the agent
- /review-game examples/flappy-bird
- review my game architecture in the current folder
- audit my game code and tell me what to fix first
How to install review-game
1Skills CLI (Vercel)
npx skills add PlayableIntelligence/game-creator --skill review-game -a claude-code2Manually: put the files in place
~/.claude/skills/review-game/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/review-game/
1Skills CLI (Vercel)
npx skills add PlayableIntelligence/game-creator --skill review-game -a codex2Manually: put the files in place
.agents/skills/review-game/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PlayableIntelligence/game-creator --skill review-game -a cursor2Manually: put the files in place
.cursor/skills/review-game/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PlayableIntelligence/game-creator review-game2Manually: put the files in place
.github/skills/review-game/SKILL.md1Skills CLI (Vercel)
npx skills add PlayableIntelligence/game-creator --skill review-game -a gemini-cli2Platform CLI
gemini skills install https://github.com/PlayableIntelligence/game-creator --path skills/review-gameManually: put the files in place
.devin/skills/review-game/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PlayableIntelligence/game-creator --skill review-game -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about review-game
How do I install review-game in Claude?
Run npx skills add PlayableIntelligence/game-creator --skill review-game -a claude-code. The skill lands at ~/.claude/skills/review-game/SKILL.md.
What does review-game do?
It reads your game code and produces a report covering architecture, performance, code quality and monetization readiness, plus prioritized recommendations and positive findings.
Does the skill fix the issues it finds?
No, it is read-only analysis. Use improve-game from the same set to implement fixes.
Source text
SKILL.md · MIT
--- name: review-game description: Review an existing game codebase for architecture, performance, and best practices. Use when the user says "review my game", "code review", "check my game architecture", "is my game well structured", or "audit my game code". Do NOT use for making changes — this is read-only analysis. Use improve-game to implement fixes. argument-hint: "[path-to-game]" license: MIT metadata: author: OpusGameLabs version: 1.3.0 tags: [game, review, architecture, best-practices, code-quality] --- ## Performance Notes - Take your time to do this thoroughly - Quality is more important than speed - Do not skip validation steps # Review Game Analyze an existing game codebase and provide a structured review. This is the final step in the pipeline — it checks everything is wired up correctly and gives you a quality score. ## Instructions Analyze the game at `$ARGUMENTS` (or the current directory if no path given). ### Step 1: Identify the game - Detect the engine (Three.js, Phaser, or other) - Read `package.json` for dependencies and scripts - Read the main entry point and index.html - Identify the game concept/genre ### Step 2: Architecture Review Check for these required patterns and report compliance: - [ ] **EventBus**: Is there a centralized event system? Are modules decoupled? - [ ] **GameState**: Is there a centralized state singleton? - [ ] **Constants**: Are config values centralized or scattered as magic numbers? - [ ] **Orchestrator**: Is there a main Game class that initializes everything? - [ ] **Directory Structure**: Is code organized into core/systems/gameplay/ui/level layers? - [ ] **Event Constants**: Are events defined as named constants or raw strings? ### Step 3: Performance Review Check for common issues: - [ ] **Delta time capping**: Is `getDelta()` capped to prevent death spirals? - [ ] **Object pooling**: Are temp objects reused in hot loops? - [ ] **Resource disposal**: Are Three.js geometries/materials/textures disposed? - [ ] **Event cleanup**: Are event listeners cleaned up on scene transitions? - [ ] **Asset loading**: Are assets preloaded with progress feedback? ### Step 4: Code Quality - [ ] **No circular dependencies**: Modules flow one direction - [ ] **Single responsibility**: Each module has one clear job - [ ] **Error handling**: Event handlers wrapped in try/catch - [ ] **Consistent naming**: Events use `domain:action`, files use PascalCase ### Step 5: Monetization Readiness - [ ] **Points system**: Is there a scoring/points mechanism? - [ ] **Session tracking**: Can game sessions be identified? - [ ] **Anti-cheat potential**: Is score validation server-side or at least structured for it? - [ ] **Play.fun integration**: Any existing SDK integration? ### Output Format Provide a structured report with: 1. **Game Overview** - What the game is, tech stack, game loop 2. **Architecture Score** (out of 6 checks) 3. **Performance Score** (out of 5 checks) 4. **Code Quality Score** (out of 4 checks) 5. **Monetization Readiness** (out of 4 checks) 6. **Top Recommendations** - Prioritized list of improvements with plain-English explanations 7. **What's Working Well** - Positive findings ## Example Usage ``` /review-game examples/flappy-bird ``` Result: Architecture 6/6, Performance 4/5, Code Quality 4/4, Monetization 2/4 → Top recommendations: add Play.fun SDK, add object pooling for pipes, add delta time capping. Positive findings: clean EventBus usage, proper GameState reset, well-organized directory structure. ## Next Step Tell the user: > Your game has been through the full pipeline! Here's what you have: > - Scaffolded architecture (`/viral-game`) > - Visual polish (`/design-game`) > - Music and sound effects (`/add-audio`) > - Automated tests (`/qa-game`) > - Architecture review (`/review-game`) > > *(Reflects the `/viral-game` one-shot pipeline. If you're working through `/make-game`, the equivalent state is "post-scaffold-phase + first development milestone shipped".)* > > **What's next?** > - Add new gameplay features with `/game-creator:add-feature [description]` > - Deploy to the web — run `npm run build && ~/.agents/skills/here-now/scripts/publish.sh dist/` for instant hosting, or use GitHub Pages, Vercel, Netlify, itch.io > - Keep iterating! Run `/design-game`, `/add-audio`, or `/review-game` again anytime after making changes.
© OpusGameLabs · MIT · PlayableIntelligence/game-creator