Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification. Orchestrate CodeWhale’s native plan state; do not build a parallel planner.
.claude/skills/hmbown-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | ＝ Same ✓ | -11% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 28% | 0% |
| case-16 | ✓→✓ | ＝ Same ✓ | -27% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -19% | 0% |
| case-07 | ✗→✗ | ＝ Same ✗ | -41% | 0% |
Use when the task is understood well enough to sequence work, but not yet a single obvious next edit.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,636 | 20,351 | -17% | 1 | 1 | 0% | 3,209 | 2,586 | -19% | 0 | 0 | — |
case-07 | fail→fail | 54,569 | 16,180 | -70% | 1 | 1 | 0% | 3,122 | 1,852 | -41% | 0 | 0 | — |
case-02 | fail→fail | 20,536 | 16,614 | -19% | 1 | 1 | 0% | 2,318 | 1,932 | -17% | 0 | 0 | — |
case-03 | fail→fail | 8,059 | 15,547 | +93% | 1 | 1 | 0% | 327 | 480 | +47% | 0 | 0 | — |
case-04 | pass→pass | 14,854 | 13,372 | -10% | 1 | 1 | 0% | 1,511 | 1,348 | -11% | 0 | 0 | — |
case-05 | pass→pass | 21,724 | 24,542 | +13% | 1 | 1 | 0% | 2,442 | 3,120 | +28% | 0 | 0 | — |
case-06 | fail→fail | 30,686 | 19,518 | -36% | 1 | 1 | 0% | 3,953 | 2,444 | -38% | 0 | 0 | — |
case-08 | fail→fail | 25,459 | 21,138 | -17% | 1 | 1 | 0% | 2,915 | 2,517 | -14% | 0 | 0 | — |
case-09 | fail→fail | 24,506 | 20,747 | -15% | 1 | 1 | 0% | 3,185 | 2,811 | -12% | 0 | 0 | — |
case-10 | fail→fail | 27,401 | 25,799 | -6% | 1 | 1 | 0% | 3,703 | 3,546 | -4% | 0 | 0 | — |
case-11 | fail→fail | 25,074 | 18,566 | -26% | 1 | 1 | 0% | 3,168 | 2,330 | -26% | 0 | 0 | — |
case-12 | fail→fail | 24,218 | 16,874 | -30% | 1 | 1 | 0% | 3,045 | 2,036 | -33% | 0 | 0 | — |
case-13 | fail→fail | 27,558 | 15,266 | -45% | 1 | 1 | 0% | 3,670 | 1,726 | -53% | 0 | 0 | — |
case-14 | fail→fail | 20,465 | 19,915 | -3% | 1 | 1 | 0% | 2,489 | 2,487 | -0% | 0 | 0 | — |
case-15 | fail→fail | 28,373 | 20,344 | -28% | 1 | 1 | 0% | 4,056 | 2,669 | -34% | 0 | 0 | — |
case-16 | pass→pass | 21,729 | 16,033 | -26% | 1 | 1 | 0% | 2,555 | 1,857 | -27% | 0 | 0 | — |
case-17 | fail→fail | 24,290 | 11,738 | -52% | 1 | 1 | 0% | 3,091 | 2,598 | -16% | 0 | 0 | — |
case-18 | fail→fail | 29,695 | 21,014 | -29% | 1 | 1 | 0% | 4,142 | 2,728 | -34% | 0 | 0 | — |
case-19 | fail→fail | 26,310 | 23,634 | -10% | 1 | 1 | 0% | 3,287 | 2,912 | -11% | 0 | 0 | — |
case-20 | fail→fail | 20,777 | 16,277 | -22% | 1 | 1 | 0% | 2,710 | 2,072 | -24% | 0 | 0 | — |
case-21 | fail→fail | 18,282 | 17,049 | -7% | 1 | 1 | 0% | 2,250 | 2,237 | -1% | 0 | 0 | — |
case-22 | fail→fail | 23,663 | 17,194 | -27% | 1 | 1 | 0% | 3,117 | 1,981 | -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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 21 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/9/2026 | +14% |
Other measured skills in the registry, with their headline benchmark lift.