Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Unity Animation skill for Animator controllers, Animation Rigging, Timeline integration, and animation state machines.
.claude/skills/a5c-ai-unity-animation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 36% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 12% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 44% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 6% | 0% |
Animation system implementation and configuration in Unity.
This skill provides capabilities for implementing character and object animation using Unity's Animator, Animation Rigging, and Timeline systems.
csharppublic class CharacterAnimator : MonoBehaviour { private Animator animator; private static readonly int SpeedHash = Animator.StringToHash("Speed"); private static readonly int JumpTrigger = Animator.StringToHash("Jump"); void Update() { float speed = GetMovementSpeed(); animator.SetFloat(SpeedHash, speed, 0.1f, Time.deltaTime); if (Input.GetButtonDown("Jump")) { animator.SetTrigger(JumpTrigger); } } }
csharp[RequireComponent(typeof(RigBuilder))] public class AimRig : MonoBehaviour { [SerializeField] private MultiAimConstraint aimConstraint; [SerializeField] private Transform aimTarget; public void SetAimWeight(float weight) { aimConstraint.weight = weight; } }
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 8,331 | 15,358 | +84% | 1 | 1 | 0% | 1,364 | 1,850 | +36% | 0 | 0 | — |
case-02 | pass→pass | 8,565 | 6,680 | -22% | 1 | 1 | 0% | 1,482 | 1,662 | +12% | 0 | 0 | — |
case-03 | pass→pass | 14,617 | 17,251 | +18% | 1 | 1 | 0% | 2,049 | 2,950 | +44% | 0 | 0 | — |
case-04 | pass→pass | 18,062 | 12,890 | -29% | 1 | 1 | 0% | 2,515 | 2,665 | +6% | 0 | 0 | — |
case-05 | pass→pass | 4,202 | 4,495 | +7% | 1 | 1 | 0% | 689 | 1,079 | +57% | 0 | 0 | — |
case-06 | pass→pass | 5,815 | 9,265 | +59% | 1 | 1 | 0% | 958 | 1,767 | +84% | 0 | 0 | — |
case-07 | pass→pass | 12,127 | 15,240 | +26% | 1 | 1 | 0% | 2,202 | 2,879 | +31% | 0 | 0 | — |
case-08 | pass→pass | 5,909 | 6,694 | +13% | 1 | 1 | 0% | 931 | 1,342 | +44% | 0 | 0 | — |
case-09 | pass→pass | 14,540 | 13,900 | -4% | 1 | 1 | 0% | 2,347 | 2,917 | +24% | 0 | 0 | — |
case-10 | pass→pass | 4,252 | 4,549 | +7% | 1 | 1 | 0% | 691 | 1,096 | +59% | 0 | 0 | — |
case-11 | pass→pass | 9,986 | 7,500 | -25% | 1 | 1 | 0% | 1,594 | 1,720 | +8% | 0 | 0 | — |
case-12 | pass→pass | 18,889 | 17,573 | -7% | 1 | 1 | 0% | 2,844 | 2,974 | +5% | 0 | 0 | — |
case-13 | pass→pass | 5,907 | 4,449 | -25% | 1 | 1 | 0% | 1,086 | 1,168 | +8% | 0 | 0 | — |
case-14 | pass→pass | 18,180 | 14,839 | -18% | 1 | 1 | 0% | 2,535 | 2,688 | +6% | 0 | 0 | — |
case-15 | pass→pass | 13,745 | 14,561 | +6% | 1 | 1 | 0% | 1,962 | 2,315 | +18% | 0 | 0 | — |
case-16 | pass→pass | 9,014 | 6,063 | -33% | 1 | 1 | 0% | 1,350 | 1,455 | +8% | 0 | 0 | — |
case-17 | pass→pass | 10,820 | 13,273 | +23% | 1 | 1 | 0% | 1,765 | 2,321 | +32% | 0 | 0 | — |
case-18 | pass→pass | 9,187 | 8,271 | -10% | 1 | 1 | 0% | 1,230 | 1,532 | +25% | 0 | 0 | — |
case-19 | pass→pass | 14,013 | 11,181 | -20% | 1 | 1 | 0% | 1,871 | 2,119 | +13% | 0 | 0 | — |
case-20 | pass→pass | 23,875 | 19,463 | -18% | 1 | 1 | 0% | 3,629 | 3,729 | +3% | 0 | 0 | — |
case-21 | pass→pass | 17,038 | 19,316 | +13% | 1 | 1 | 0% | 2,374 | 3,180 | +34% | 0 | 0 | — |
case-22 | fail→pass | 12,653 | 11,554 | -9% | 1 | 1 | 0% | 1,861 | 2,575 | +38% | 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. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 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.