Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
.claude/skills/dokhacgiakhoa-dbt-transformation-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 6% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -13% | 0% |
Production-ready patterns for dbt (data build tool) including model organization, testing strategies, documentation, and incremental processing.
resources/implementation-playbook.md.resources/implementation-playbook.md for detailed dbt patterns and examples.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 21,053 | 25,690 | +22% | 1 | 1 | 0% | 4,016 | 3,504 | -13% | 0 | 0 | — |
case-02 | pass→pass | 15,734 | 12,514 | -20% | 1 | 1 | 0% | 2,357 | 2,504 | +6% | 0 | 0 | — |
case-03 | pass→pass | 14,082 | 9,926 | -30% | 1 | 1 | 0% | 2,269 | 1,984 | -13% | 0 | 0 | — |
case-04 | fail→pass | 15,254 | 11,925 | -22% | 1 | 1 | 0% | 2,530 | 2,037 | -19% | 0 | 0 | — |
case-05 | pass→pass | 14,051 | 9,888 | -30% | 1 | 1 | 0% | 2,442 | 1,947 | -20% | 0 | 0 | — |
case-06 | pass→pass | 14,975 | 10,541 | -30% | 1 | 1 | 0% | 2,348 | 2,118 | -10% | 0 | 0 | — |
case-07 | pass→pass | 15,837 | 12,743 | -20% | 1 | 1 | 0% | 2,787 | 2,451 | -12% | 0 | 0 | — |
case-08 | pass→pass | 14,744 | 13,509 | -8% | 1 | 1 | 0% | 2,342 | 2,766 | +18% | 0 | 0 | — |
case-09 | pass→pass | 18,258 | 17,344 | -5% | 1 | 1 | 0% | 2,709 | 3,427 | +27% | 0 | 0 | — |
case-10 | pass→pass | 14,138 | 9,247 | -35% | 1 | 1 | 0% | 2,415 | 2,107 | -13% | 0 | 0 | — |
case-11 | pass→pass | 18,502 | 12,990 | -30% | 1 | 1 | 0% | 2,609 | 2,454 | -6% | 0 | 0 | — |
case-12 | pass→pass | 17,170 | 13,705 | -20% | 1 | 1 | 0% | 2,812 | 2,457 | -13% | 0 | 0 | — |
case-13 | pass→pass | 18,118 | 10,371 | -43% | 1 | 1 | 0% | 2,906 | 2,068 | -29% | 0 | 0 | — |
case-14 | fail→pass | 18,973 | 13,152 | -31% | 1 | 1 | 0% | 2,811 | 2,772 | -1% | 0 | 0 | — |
case-15 | fail→pass | 9,125 | 6,888 | -25% | 1 | 1 | 0% | 1,608 | 1,612 | +0% | 0 | 0 | — |
case-16 | pass→pass | 21,410 | 13,758 | -36% | 1 | 1 | 0% | 2,984 | 2,029 | -32% | 0 | 0 | — |
case-17 | pass→pass | 15,134 | 10,732 | -29% | 1 | 1 | 0% | 2,686 | 2,191 | -18% | 0 | 0 | — |
case-18 | pass→pass | 14,817 | 14,050 | -5% | 1 | 1 | 0% | 2,369 | 2,918 | +23% | 0 | 0 | — |
case-19 | pass→pass | 10,752 | 6,892 | -36% | 1 | 1 | 0% | 1,729 | 1,451 | -16% | 0 | 0 | — |
case-20 | pass→pass | 17,990 | 13,459 | -25% | 1 | 1 | 0% | 2,618 | 2,523 | -4% | 0 | 0 | — |
case-21 | pass→pass | 4,079 | 5,815 | +43% | 1 | 1 | 0% | 728 | 1,180 | +62% | 0 | 0 | — |
case-22 | pass→pass | 14,976 | 12,305 | -18% | 1 | 1 | 0% | 2,369 | 2,354 | -1% | 0 | 0 | — |
case-23 | pass→pass | 22,931 | 15,581 | -32% | 1 | 1 | 0% | 3,436 | 3,207 | -7% | 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. 23 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 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.