Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and constraints, and scroll/interaction-friendly canvas scenes.
.claude/skills/mengto-matterjs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-02 | ✓→✗ | ▼ Worse | 3% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 12% | 0% |
html<script> const { Engine, Render, Runner, Bodies, Composite } = Matter; const engine = Engine.create(); const render = Render.create({ element: document.body, engine: engine, options: { width: 800, height: 600, wireframes: false } }); const runner = Runner.create(); Runner.run(runner, engine); Render.run(render); const ground = Bodies.rectangle(400, 610, 810, 60, { isStatic: true }); const box = Bodies.rectangle(400, 200, 80, 80); Composite.add(engine.world, [ground, box]); </script>
Composite.add(engine.world, [...]) to add bodies to the world.Render.create({ element, engine }) to create a canvas automatically, or pass a canvas you create yourself.render.options.wireframes = false for solid rendering.Runner.run(runner, engine) for a simple loop, or call Engine.update in your own loop if you need custom timing.jsconst { Mouse, MouseConstraint } = Matter; const mouse = Mouse.create(render.canvas); const mouseConstraint = MouseConstraint.create(engine, { mouse }); Composite.add(engine.world, mouseConstraint); render.mouse = mouse;
Runner.stop(runner).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,002 | 7,104 | +1% | 1 | 1 | 0% | 1,610 | 2,152 | +34% | 0 | 0 | — |
case-02 | pass→fail | 12,484 | 9,884 | -21% | 1 | 1 | 0% | 2,700 | 2,791 | +3% | 0 | 0 | — |
case-03 | fail→fail | 15,472 | 11,912 | -23% | 1 | 1 | 0% | 3,652 | 3,225 | -12% | 0 | 0 | — |
case-04 | pass→pass | 6,767 | 4,306 | -36% | 1 | 1 | 0% | 1,361 | 1,531 | +12% | 0 | 0 | — |
case-05 | pass→pass | 6,726 | 3,762 | -44% | 1 | 1 | 0% | 1,357 | 1,287 | -5% | 0 | 0 | — |
case-06 | pass→pass | 8,963 | 5,202 | -42% | 1 | 1 | 0% | 1,858 | 1,585 | -15% | 0 | 0 | — |
case-07 | pass→pass | 3,527 | 2,930 | -17% | 1 | 1 | 0% | 671 | 1,165 | +74% | 0 | 0 | — |
case-08 | pass→pass | 12,961 | 8,154 | -37% | 1 | 1 | 0% | 2,281 | 1,948 | -15% | 0 | 0 | — |
case-13 | pass→pass | 4,673 | 2,922 | -37% | 1 | 1 | 0% | 966 | 1,088 | +13% | 0 | 0 | — |
case-09 | fail→pass | 14,071 | 4,293 | -69% | 1 | 1 | 0% | 3,237 | 1,458 | -55% | 0 | 0 | — |
case-10 | pass→pass | 7,264 | 3,728 | -49% | 1 | 1 | 0% | 1,368 | 1,237 | -10% | 0 | 0 | — |
case-11 | pass→pass | 10,286 | 5,228 | -49% | 1 | 1 | 0% | 2,087 | 1,632 | -22% | 0 | 0 | — |
case-12 | pass→pass | 12,734 | 2,756 | -78% | 1 | 1 | 0% | 2,700 | 1,092 | -60% | 0 | 0 | — |
case-14 | pass→pass | 7,308 | 3,056 | -58% | 1 | 1 | 0% | 1,230 | 1,101 | -10% | 0 | 0 | — |
case-15 | fail→pass | 7,972 | 3,040 | -62% | 1 | 1 | 0% | 1,243 | 1,083 | -13% | 0 | 0 | — |
case-16 | pass→pass | 14,521 | 11,844 | -18% | 1 | 1 | 0% | 2,575 | 2,687 | +4% | 0 | 0 | — |
case-17 | pass→pass | 8,474 | 3,237 | -62% | 1 | 1 | 0% | 1,545 | 1,182 | -23% | 0 | 0 | — |
case-18 | fail→pass | 18,190 | 8,942 | -51% | 1 | 1 | 0% | 3,181 | 2,436 | -23% | 0 | 0 | — |
case-19 | pass→pass | 6,159 | 3,822 | -38% | 1 | 1 | 0% | 1,204 | 1,277 | +6% | 0 | 0 | — |
case-20 | pass→pass | 8,881 | 5,275 | -41% | 1 | 1 | 0% | 1,838 | 1,648 | -10% | 0 | 0 | — |
case-21 | pass→pass | 10,120 | 8,911 | -12% | 1 | 1 | 0% | 2,271 | 2,631 | +16% | 0 | 0 | — |
case-22 | pass→pass | 13,744 | 12,674 | -8% | 1 | 1 | 0% | 2,952 | 3,244 | +10% | 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 +9 percentage points is the difference between those two pass rates over the 22 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.