Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature implementation, skipped validation, and unreviewed high-risk designs.
.claude/skills/dokhacgiakhoa-design-orchestration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -63% | 0% |
Ensure that ideas become designs, designs are reviewed, and only validated designs reach implementation.
This skill does not generate designs. It controls the flow between other skills.
This is a routing and enforcement skill, not a creative one.
It decides:
This meta-skill coordinates the following:
brainstorming — design generationmulti-agent-brainstorming — design validationInvoke this skill when:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,818 | 21,962 | -21% | 1 | 1 | 0% | 5,040 | 3,826 | -24% | 0 | 0 | — |
case-13 | fail→pass | 25,739 | 18,091 | -30% | 1 | 1 | 0% | 3,558 | 2,894 | -19% | 0 | 0 | — |
case-02 | fail→fail | 31,618 | 23,494 | -26% | 1 | 1 | 0% | 6,017 | 3,589 | -40% | 0 | 0 | — |
case-03 | fail→fail | 42,012 | 20,060 | -52% | 1 | 1 | 0% | 6,578 | 3,749 | -43% | 0 | 0 | — |
case-04 | pass→pass | 13,989 | 10,093 | -28% | 1 | 1 | 0% | 2,219 | 2,074 | -7% | 0 | 0 | — |
case-05 | pass→pass | 6,294 | 5,482 | -13% | 1 | 1 | 0% | 1,211 | 1,336 | +10% | 0 | 0 | — |
case-06 | pass→pass | 7,388 | 6,351 | -14% | 1 | 1 | 0% | 1,250 | 1,517 | +21% | 0 | 0 | — |
case-07 | fail→fail | 46,151 | 18,867 | -59% | 1 | 1 | 0% | 7,091 | 2,971 | -58% | 0 | 0 | — |
case-08 | pass→pass | 23,632 | 12,960 | -45% | 1 | 1 | 0% | 3,457 | 2,515 | -27% | 0 | 0 | — |
case-09 | fail→fail | 16,959 | 31,618 | +86% | 1 | 1 | 0% | 3,157 | 5,204 | +65% | 0 | 0 | — |
case-10 | fail→pass | 19,360 | 16,026 | -17% | 1 | 1 | 0% | 3,305 | 2,370 | -28% | 0 | 0 | — |
case-11 | fail→pass | 26,650 | 16,737 | -37% | 1 | 1 | 0% | 4,582 | 2,970 | -35% | 0 | 0 | — |
case-12 | fail→pass | 18,159 | 15,487 | -15% | 1 | 1 | 0% | 2,941 | 2,472 | -16% | 0 | 0 | — |
case-14 | fail→pass | 30,841 | 12,704 | -59% | 1 | 1 | 0% | 5,955 | 2,226 | -63% | 0 | 0 | — |
case-15 | fail→pass | 17,908 | 22,275 | +24% | 1 | 1 | 0% | 2,662 | 3,931 | +48% | 0 | 0 | — |
case-16 | fail→fail | 14,508 | 24,406 | +68% | 1 | 1 | 0% | 2,608 | 4,873 | +87% | 0 | 0 | — |
case-17 | pass→pass | 17,849 | 12,144 | -32% | 1 | 1 | 0% | 2,683 | 2,420 | -10% | 0 | 0 | — |
case-18 | fail→pass | 33,269 | 13,010 | -61% | 1 | 1 | 0% | 5,477 | 2,444 | -55% | 0 | 0 | — |
case-19 | fail→pass | 18,500 | 27,985 | +51% | 1 | 1 | 0% | 2,763 | 4,050 | +47% | 0 | 0 | — |
case-20 | pass→pass | 20,422 | 16,417 | -20% | 1 | 1 | 0% | 2,935 | 2,923 | -0% | 0 | 0 | — |
case-21 | fail→pass | 22,137 | 12,213 | -45% | 1 | 1 | 0% | 3,836 | 2,373 | -38% | 0 | 0 | — |
case-22 | fail→pass | 29,475 | 12,431 | -58% | 1 | 1 | 0% | 4,236 | 2,527 | -40% | 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 +45 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.