Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Game development orchestrator. Routes to platform-specific skills based on project needs.
.claude/skills/lingxling-game-development/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 14% | 0% |
> Orchestrator skill that provides core principles and routes to specialized sub-skills.
You are working on a game development project. This skill teaches the PRINCIPLES of game development and directs you to the right sub-skill based on context.
| If the game targets... | Use Sub-Skill | |------------------------|---------------| | Web browsers (HTML5, WebGL) | game-development/web-games | | Mobile (iOS, Android) | game-development/mobile-games | | PC (Steam, Desktop) | game-development/pc-games | | VR/AR headsets | game-development/vr-ar |
| If the game is... | Use Sub-Skill | |-------------------|---------------| | 2D (sprites, tilemaps) | game-development/2d-games | | 3D (meshes, shaders) | game-development/3d-games |
| If you need... | Use Sub-Skill | |----------------|---------------| | GDD, balancing, player psychology | game-development/game-design | | Multiplayer, networking | game-development/multiplayer | | Visual style, asset pipeline, animation | game-development/game-art | | Sound design, music, adaptive audio | game-development/game-audio |
Every game, regardless of platform, follows this pattern:
INPUT → Read player actions
UPDATE → Process game logic (fixed timestep)
RENDER → Draw the frame (interpolated)Fixed Timestep Rule:
| Pattern | Use When | Example | |---------|----------|---------| | State Machine | 3-5 discrete states | Player: Idle→Walk→Jump | | Object Pooling | Frequent spawn/destroy | Bullets, particles | | Observer/Events | Cross-system communication | Health→UI updates | | ECS | Thousands of similar entities | RTS units, particles | | Command | Undo, replay, networking | Input recording | | Behavior Tree | Complex AI decisions | Enemy AI |
Decision Rule: Start with State Machine. Add ECS only when performance demands.
Abstract input into ACTIONS, not raw keys:
"jump" → Space, Gamepad A, Touch tap
"move" → WASD, Left stick, Virtual joystickWhy: Enables multi-platform, rebindable controls.
| System | Budget | |--------|--------| | Input | 1ms | | Physics | 3ms | | AI | 2ms | | Game Logic | 4ms | | Rendering | 5ms | | Buffer | 1.67ms |
Optimization Priority:
| AI Type | Complexity | Use When | |---------|------------|----------| | FSM | Simple | 3-5 states, predictable behavior | | Behavior Tree | Medium | Modular, designer-friendly | | GOAP | High | Emergent, planning-based | | Utility AI | High | Scoring-based decisions |
| Type | Best For | |------|----------| | AABB | Rectangles, fast checks | | Circle | Round objects, cheap | | Spatial Hash | Many similar-sized objects | | Quadtree | Large worlds, varying sizes |
| Don't | Do | |-------|-----| | Update everything every frame | Use events, dirty flags | | Create objects in hot loops | Object pooling | | Cache nothing | Cache references | | Optimize without profiling | Profile first | | Mix input with logic | Abstract input layer |
→ Start with game-development/web-games for framework selection → Then game-development/2d-games for sprite/tilemap patterns → Reference game-development/game-design for level design
→ Start with game-development/mobile-games for touch input and stores → Use game-development/game-design for puzzle balancing
→ game-development/vr-ar for comfort and immersion → game-development/3d-games for rendering → game-development/multiplayer for networking
> Remember: Great games come from iteration, not perfection. Prototype fast, then polish.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 54,700 | 24,819 | -55% | 1 | 1 | 0% | 8,273 | 5,102 | -38% | 0 | 0 | — |
case-22 | fail→fail | 21,584 | 30,613 | +42% | 1 | 1 | 0% | 4,451 | 6,067 | +36% | 0 | 0 | — |
case-01 | fail→fail | 38,145 | 25,826 | -32% | 1 | 1 | 0% | 5,455 | 4,481 | -18% | 0 | 0 | — |
case-03 | pass→pass | 55,393 | 39,848 | -28% | 1 | 1 | 0% | 8,291 | 6,712 | -19% | 0 | 0 | — |
case-04 | pass→pass | 28,374 | 26,624 | -6% | 1 | 1 | 0% | 4,063 | 5,038 | +24% | 0 | 0 | — |
case-05 | fail→pass | 23,999 | 13,697 | -43% | 1 | 1 | 0% | 3,242 | 3,187 | -2% | 0 | 0 | — |
case-06 | pass→pass | 25,197 | 15,025 | -40% | 1 | 1 | 0% | 3,796 | 3,756 | -1% | 0 | 0 | — |
case-07 | fail→fail | 19,051 | 20,406 | +7% | 1 | 1 | 0% | 3,017 | 4,668 | +55% | 0 | 0 | — |
case-08 | pass→pass | 20,166 | 15,308 | -24% | 1 | 1 | 0% | 2,710 | 3,743 | +38% | 0 | 0 | — |
case-09 | pass→pass | 17,178 | 17,923 | +4% | 1 | 1 | 0% | 2,663 | 3,891 | +46% | 0 | 0 | — |
case-10 | pass→pass | 18,699 | 16,494 | -12% | 1 | 1 | 0% | 2,925 | 4,018 | +37% | 0 | 0 | — |
case-11 | pass→pass | 21,907 | 14,821 | -32% | 1 | 1 | 0% | 3,958 | 3,880 | -2% | 0 | 0 | — |
case-12 | pass→pass | 15,090 | 13,390 | -11% | 1 | 1 | 0% | 2,550 | 3,578 | +40% | 0 | 0 | — |
case-13 | fail→pass | 8,608 | 2,446 | -72% | 1 | 1 | 0% | 1,309 | 1,750 | +34% | 0 | 0 | — |
case-14 | pass→pass | 10,956 | 3,180 | -71% | 1 | 1 | 0% | 1,783 | 1,704 | -4% | 0 | 0 | — |
case-15 | pass→pass | 8,302 | 1,907 | -77% | 1 | 1 | 0% | 1,179 | 1,660 | +41% | 0 | 0 | — |
case-16 | pass→pass | 23,442 | 21,067 | -10% | 1 | 1 | 0% | 3,634 | 4,703 | +29% | 0 | 0 | — |
case-17 | pass→pass | 9,331 | 8,395 | -10% | 1 | 1 | 0% | 1,360 | 2,404 | +77% | 0 | 0 | — |
case-18 | fail→pass | 18,221 | 9,808 | -46% | 1 | 1 | 0% | 2,728 | 2,813 | +3% | 0 | 0 | — |
case-19 | fail→pass | 9,006 | 2,420 | -73% | 1 | 1 | 0% | 1,203 | 1,612 | +34% | 0 | 0 | — |
case-20 | fail→fail | 8,285 | 21,797 | +163% | 1 | 1 | 0% | 1,407 | 3,114 | +121% | 0 | 0 | — |
case-21 | fail→pass | 16,281 | 8,839 | -46% | 1 | 1 | 0% | 2,510 | 2,861 | +14% | 0 | 0 | — |
case-23 | pass→pass | 13,976 | 7,836 | -44% | 1 | 1 | 0% | 2,170 | 2,550 | +18% | 0 | 0 | — |
case-24 | pass→pass | 16,035 | 11,966 | -25% | 1 | 1 | 0% | 2,699 | 3,303 | +22% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +21 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.