Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Game design principles. GDD structure, balancing, player psychology, progression.
.claude/skills/lingxling-game-design/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-25 | ✓→✗ | ▼ Worse | -8% | 0% |
> Design thinking for engaging games.
Every game needs a fun 30-second loop:
1. ACTION → Player does something
2. FEEDBACK → Game responds
3. REWARD → Player feels good
4. REPEAT| Genre | Core Loop | |-------|-----------| | Platformer | Run → Jump → Land → Collect | | Shooter | Aim → Shoot → Kill → Loot | | Puzzle | Observe → Think → Solve → Advance | | RPG | Explore → Fight → Level → Gear |
| Section | Content | |---------|---------| | Pitch | One-sentence description | | Core Loop | 30-second gameplay | | Mechanics | How systems work | | Progression | How player advances | | Art Style | Visual direction | | Audio | Sound direction |
| Type | Driven By | |------|-----------| | Achiever | Goals, completion | | Explorer | Discovery, secrets | | Socializer | Interaction, community | | Killer | Competition, dominance |
| Schedule | Effect | Use | |----------|--------|-----| | Fixed | Predictable | Milestone rewards | | Variable | Addictive | Loot drops | | Ratio | Effort-based | Grind games |
Too Hard → Frustration → Quit
Too Easy → Boredom → Quit
Just Right → Flow → Engagement| Strategy | How | |----------|-----| | Dynamic | Adjust to player skill | | Selection | Let player choose | | Accessibility | Options for all |
| Type | Example | |------|---------| | Skill | Player gets better | | Power | Character gets stronger | | Content | New areas unlock | | Story | Narrative advances |
| ❌ Don't | ✅ Do | |----------|-------| | Design in isolation | Playtest constantly | | Polish before fun | Prototype first | | Force one way to play | Allow player expression | | Punish excessively | Reward progress |
> Remember: Fun is discovered through iteration, not designed on paper.
This skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,953 | 20,957 | -22% | 1 | 1 | 0% | 3,501 | 3,024 | -14% | 0 | 0 | — |
case-02 | fail→fail | 21,680 | 12,786 | -41% | 1 | 1 | 0% | 3,036 | 2,737 | -10% | 0 | 0 | — |
case-03 | fail→fail | 15,794 | 10,819 | -31% | 1 | 1 | 0% | 2,433 | 2,142 | -12% | 0 | 0 | — |
case-04 | fail→pass | 12,533 | 3,222 | -74% | 1 | 1 | 0% | 1,896 | 1,219 | -36% | 0 | 0 | — |
case-05 | fail→fail | 13,446 | 9,793 | -27% | 1 | 1 | 0% | 1,824 | 2,209 | +21% | 0 | 0 | — |
case-06 | fail→pass | 17,663 | 8,557 | -52% | 1 | 1 | 0% | 2,507 | 2,042 | -19% | 0 | 0 | — |
case-07 | pass→pass | 16,887 | 10,179 | -40% | 1 | 1 | 0% | 2,503 | 2,276 | -9% | 0 | 0 | — |
case-13 | pass→pass | 19,556 | 10,531 | -46% | 1 | 1 | 0% | 2,720 | 2,289 | -16% | 0 | 0 | — |
case-08 | pass→pass | 10,470 | 3,541 | -66% | 1 | 1 | 0% | 1,650 | 1,234 | -25% | 0 | 0 | — |
case-09 | fail→pass | 8,212 | 3,741 | -54% | 1 | 1 | 0% | 1,328 | 1,319 | -1% | 0 | 0 | — |
case-10 | pass→pass | 16,662 | 14,865 | -11% | 1 | 1 | 0% | 2,119 | 2,777 | +31% | 0 | 0 | — |
case-11 | pass→pass | 17,364 | 12,554 | -28% | 1 | 1 | 0% | 2,327 | 2,431 | +4% | 0 | 0 | — |
case-12 | fail→pass | 18,456 | 3,840 | -79% | 1 | 1 | 0% | 3,047 | 1,168 | -62% | 0 | 0 | — |
case-14 | pass→pass | 18,855 | 7,663 | -59% | 1 | 1 | 0% | 2,655 | 1,780 | -33% | 0 | 0 | — |
case-15 | pass→pass | 18,241 | 9,726 | -47% | 1 | 1 | 0% | 2,550 | 2,147 | -16% | 0 | 0 | — |
case-16 | pass→pass | 14,262 | 3,574 | -75% | 1 | 1 | 0% | 1,622 | 1,214 | -25% | 0 | 0 | — |
case-17 | pass→pass | 19,426 | 26,122 | +34% | 1 | 1 | 0% | 3,419 | 4,407 | +29% | 0 | 0 | — |
case-18 | pass→pass | 17,096 | 14,366 | -16% | 1 | 1 | 0% | 2,463 | 2,822 | +15% | 0 | 0 | — |
case-19 | pass→pass | 14,362 | 12,875 | -10% | 1 | 1 | 0% | 2,268 | 2,619 | +15% | 0 | 0 | — |
case-20 | pass→pass | 16,953 | 8,377 | -51% | 1 | 1 | 0% | 2,853 | 1,887 | -34% | 0 | 0 | — |
case-21 | fail→fail | 17,057 | 3,312 | -81% | 1 | 1 | 0% | 2,239 | 1,221 | -45% | 0 | 0 | — |
case-22 | pass→pass | 11,481 | 4,515 | -61% | 1 | 1 | 0% | 1,836 | 1,261 | -31% | 0 | 0 | — |
case-23 | pass→pass | 5,618 | 2,457 | -56% | 1 | 1 | 0% | 919 | 1,064 | +16% | 0 | 0 | — |
case-24 | pass→pass | 15,815 | 10,136 | -36% | 1 | 1 | 0% | 2,147 | 2,106 | -2% | 0 | 0 | — |
case-25 | pass→fail | 9,484 | 4,201 | -56% | 1 | 1 | 0% | 1,393 | 1,288 | -8% | 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. 25 cases were attempted. The headline lift of +12 percentage points is the difference between those two pass rates over the 25 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.