Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
.claude/skills/dokhacgiakhoa-algorithmic-art/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 91% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 360% | 0% |
| case-03 | ✓→✗ | ▼ Worse | 127% | 0% |
Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).
This happens in two steps:
First, undertake this task:
To begin, create an ALGORITHMIC PHILOSOPHY (not static images or templates) that will be interpreted through:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 52,334 | 61,107 | +17% | 1 | 1 | 0% | 8,243 | 8,694 | +5% | 0 | 0 | — |
case-02 | fail→fail | 41,191 | 51,634 | +25% | 1 | 1 | 0% | 8,250 | 8,701 | +5% | 0 | 0 | — |
case-03 | pass→fail | 18,776 | 42,479 | +126% | 1 | 1 | 0% | 3,835 | 8,694 | +127% | 0 | 0 | — |
case-04 | pass→fail | 13,925 | 49,784 | +258% | 1 | 1 | 0% | 2,311 | 8,682 | +276% | 0 | 0 | — |
case-05 | pass→pass | 18,208 | 39,073 | +115% | 1 | 1 | 0% | 3,726 | 8,698 | +133% | 0 | 0 | — |
case-06 | fail→fail | 31,958 | 40,087 | +25% | 1 | 1 | 0% | 8,240 | 8,691 | +5% | 0 | 0 | — |
case-07 | fail→pass | 24,484 | 40,310 | +65% | 1 | 1 | 0% | 4,554 | 8,679 | +91% | 0 | 0 | — |
case-08 | fail→fail | 27,193 | 49,919 | +84% | 1 | 1 | 0% | 4,357 | 8,673 | +99% | 0 | 0 | — |
case-09 | fail→fail | 27,159 | 43,391 | +60% | 1 | 1 | 0% | 5,887 | 8,677 | +47% | 0 | 0 | — |
case-10 | fail→pass | 33,518 | 40,666 | +21% | 1 | 1 | 0% | 5,216 | 8,680 | +66% | 0 | 0 | — |
case-11 | fail→pass | 30,541 | 54,362 | +78% | 1 | 1 | 0% | 4,872 | 8,675 | +78% | 0 | 0 | — |
case-12 | fail→fail | 46,539 | 42,255 | -9% | 1 | 1 | 0% | 8,217 | 8,668 | +5% | 0 | 0 | — |
case-13 | fail→fail | 52,511 | 49,335 | -6% | 1 | 1 | 0% | 8,223 | 8,674 | +5% | 0 | 0 | — |
case-14 | fail→fail | 16,672 | 47,632 | +186% | 1 | 1 | 0% | 3,669 | 8,676 | +136% | 0 | 0 | — |
case-15 | fail→fail | 19,053 | 40,849 | +114% | 1 | 1 | 0% | 4,463 | 8,664 | +94% | 0 | 0 | — |
case-16 | pass→pass | 19,876 | 51,717 | +160% | 1 | 1 | 0% | 3,125 | 8,677 | +178% | 0 | 0 | — |
case-17 | fail→fail | 34,050 | 47,462 | +39% | 1 | 1 | 0% | 8,236 | 8,687 | +5% | 0 | 0 | — |
case-18 | fail→fail | 38,919 | 45,621 | +17% | 1 | 1 | 0% | 6,285 | 8,671 | +38% | 0 | 0 | — |
case-19 | pass→fail | 27,057 | 42,594 | +57% | 1 | 1 | 0% | 4,197 | 8,673 | +107% | 0 | 0 | — |
case-20 | fail→fail | 33,820 | 45,837 | +36% | 1 | 1 | 0% | 6,190 | 8,676 | +40% | 0 | 0 | — |
case-21 | fail→fail | 38,885 | 44,087 | +13% | 1 | 1 | 0% | 6,395 | 8,670 | +36% | 0 | 0 | — |
case-22 | fail→pass | 12,340 | 45,445 | +268% | 1 | 1 | 0% | 1,693 | 7,789 | +360% | 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. 3 cases got worse with the skill loaded, and they are 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.