Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
.claude/skills/wshobson-workflow-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -50% | 0% |
Guide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, handling git commits, and executing the verification protocol that ensures quality throughout implementation.
Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 10,968 | 6,342 | -42% | 1 | 1 | 0% | 1,734 | 1,224 | -29% | 0 | 0 | — |
case-01 | pass→pass | 13,258 | 9,416 | -29% | 1 | 1 | 0% | 2,182 | 2,197 | +1% | 0 | 0 | — |
case-02 | fail→pass | 11,686 | 7,476 | -36% | 1 | 1 | 0% | 2,229 | 1,741 | -22% | 0 | 0 | — |
case-03 | fail→fail | 10,208 | 6,348 | -38% | 1 | 1 | 0% | 1,805 | 1,540 | -15% | 0 | 0 | — |
case-04 | pass→pass | 15,668 | 14,204 | -9% | 1 | 1 | 0% | 2,556 | 2,502 | -2% | 0 | 0 | — |
case-05 | pass→pass | 8,895 | 8,285 | -7% | 1 | 1 | 0% | 2,005 | 2,053 | +2% | 0 | 0 | — |
case-06 | pass→pass | 8,480 | 8,621 | +2% | 1 | 1 | 0% | 1,902 | 2,004 | +5% | 0 | 0 | — |
case-07 | pass→pass | 10,008 | 3,516 | -65% | 1 | 1 | 0% | 1,535 | 927 | -40% | 0 | 0 | — |
case-08 | pass→pass | 9,692 | 5,195 | -46% | 1 | 1 | 0% | 1,656 | 1,245 | -25% | 0 | 0 | — |
case-09 | pass→pass | 5,987 | 2,421 | -60% | 1 | 1 | 0% | 1,021 | 697 | -32% | 0 | 0 | — |
case-10 | fail→pass | 9,053 | 2,956 | -67% | 1 | 1 | 0% | 1,574 | 765 | -51% | 0 | 0 | — |
case-12 | fail→pass | 9,465 | 5,120 | -46% | 1 | 1 | 0% | 1,684 | 1,062 | -37% | 0 | 0 | — |
case-13 | fail→pass | 9,852 | 3,672 | -63% | 1 | 1 | 0% | 1,587 | 960 | -40% | 0 | 0 | — |
case-14 | pass→pass | 7,849 | 4,662 | -41% | 1 | 1 | 0% | 1,396 | 1,134 | -19% | 0 | 0 | — |
case-15 | fail→fail | 8,493 | 6,598 | -22% | 1 | 1 | 0% | 1,456 | 1,434 | -2% | 0 | 0 | — |
case-16 | fail→pass | 11,517 | 4,366 | -62% | 1 | 1 | 0% | 2,006 | 998 | -50% | 0 | 0 | — |
case-17 | pass→pass | 8,466 | 3,788 | -55% | 1 | 1 | 0% | 1,537 | 988 | -36% | 0 | 0 | — |
case-18 | fail→pass | 11,879 | 1,191 | -90% | 1 | 1 | 0% | 1,967 | 479 | -76% | 0 | 0 | — |
case-19 | pass→pass | 7,273 | 3,413 | -53% | 1 | 1 | 0% | 1,224 | 907 | -26% | 0 | 0 | — |
case-20 | pass→pass | 3,415 | 2,634 | -23% | 1 | 1 | 0% | 614 | 692 | +13% | 0 | 0 | — |
case-21 | fail→pass | 11,009 | 2,442 | -78% | 1 | 1 | 0% | 1,812 | 648 | -64% | 0 | 0 | — |
case-22 | pass→pass | 11,301 | 5,636 | -50% | 1 | 1 | 0% | 1,993 | 1,281 | -36% | 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 +32 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.