Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities.
.claude/skills/sickn33-interactive-portfolio/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 162% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 129% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 169% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 91% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 121% | 0% |
Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities.
Role: Portfolio Experience Designer
You know a portfolio isn't a resume - it's a first impression that needs to convert. You balance creativity with usability. You understand that hiring managers spend 30 seconds on each portfolio. You make those 30 seconds count. You help people stand out without being gimmicky.
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 21,350 | 37,708 | +77% | 1 | 1 | 0% | 3,357 | 5,870 | +75% | 0 | 0 | — |
case-02 | fail→fail | 17,367 | 14,700 | -15% | 1 | 1 | 0% | 2,628 | 5,119 | +95% | 0 | 0 | — |
case-03 | pass→pass | 14,614 | 11,572 | -21% | 1 | 1 | 0% | 2,439 | 4,668 | +91% | 0 | 0 | — |
case-04 | pass→pass | 12,108 | 11,328 | -6% | 1 | 1 | 0% | 2,147 | 4,750 | +121% | 0 | 0 | — |
case-05 | pass→pass | 15,692 | 13,139 | -16% | 1 | 1 | 0% | 2,415 | 4,955 | +105% | 0 | 0 | — |
case-06 | pass→pass | 11,893 | 13,141 | +10% | 1 | 1 | 0% | 2,024 | 4,908 | +142% | 0 | 0 | — |
case-07 | pass→pass | 15,552 | 13,024 | -16% | 1 | 1 | 0% | 2,371 | 4,756 | +101% | 0 | 0 | — |
case-08 | fail→fail | 15,847 | 13,775 | -13% | 1 | 1 | 0% | 2,335 | 4,998 | +114% | 0 | 0 | — |
case-09 | pass→pass | 12,987 | 11,158 | -14% | 1 | 1 | 0% | 2,108 | 4,823 | +129% | 0 | 0 | — |
case-10 | pass→fail | 14,242 | 19,597 | +38% | 1 | 1 | 0% | 2,276 | 6,113 | +169% | 0 | 0 | — |
case-11 | pass→pass | 17,897 | 15,485 | -13% | 1 | 1 | 0% | 2,736 | 5,043 | +84% | 0 | 0 | — |
case-12 | pass→pass | 4,226 | 4,501 | +7% | 1 | 1 | 0% | 738 | 3,613 | +390% | 0 | 0 | — |
case-13 | pass→pass | 13,984 | 13,481 | -4% | 1 | 1 | 0% | 2,501 | 5,261 | +110% | 0 | 0 | — |
case-14 | pass→pass | 11,752 | 4,060 | -65% | 1 | 1 | 0% | 1,726 | 3,488 | +102% | 0 | 0 | — |
case-15 | fail→pass | 8,787 | 4,780 | -46% | 1 | 1 | 0% | 1,359 | 3,565 | +162% | 0 | 0 | — |
case-16 | pass→pass | 8,938 | 5,528 | -38% | 1 | 1 | 0% | 1,373 | 3,678 | +168% | 0 | 0 | — |
case-17 | pass→pass | 17,768 | 16,587 | -7% | 1 | 1 | 0% | 2,734 | 5,366 | +96% | 0 | 0 | — |
case-18 | pass→pass | 16,931 | 15,168 | -10% | 1 | 1 | 0% | 2,531 | 4,828 | +91% | 0 | 0 | — |
case-19 | fail→pass | 12,552 | 11,205 | -11% | 1 | 1 | 0% | 2,040 | 4,665 | +129% | 0 | 0 | — |
case-20 | fail→fail | 11,186 | 11,661 | +4% | 1 | 1 | 0% | 2,130 | 5,156 | +142% | 0 | 0 | — |
case-21 | fail→fail | 18,424 | 28,288 | +54% | 1 | 1 | 0% | 3,592 | 8,530 | +137% | 0 | 0 | — |
case-22 | fail→fail | 19,885 | 19,012 | -4% | 1 | 1 | 0% | 4,079 | 6,516 | +60% | 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. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.