Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Takes a manual business workflow description and designs the automated version. Maps current steps, handoffs, decision points, and bottlenecks. Designs automated flow with triggers, conditions, actions, and error handling. Outputs workflow-automation.md with before/after Mermaid diagrams, tool recommendations, implementation steps, and time savings estimate.
.claude/skills/onewave-ai-workflow-automator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 280% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 48% | 0% |
Transform a manual business workflow into an optimized automated system: map how work gets done today, then design a complete automated replacement with triggers, conditions, actions, branching, and error handling. Deliver a comprehensive workflow-automation.md.
references/intake.md -- What to gather and how to ask for missing detailreferences/analysis-framework.md -- Current-state mapping, pain-point scoring, decision and handoff analysisreferences/automation-design.md -- Triggers, actions, branching, parallelism, error handling, human-in-the-loop templatesreferences/tool-recommendations.md -- Platform decision matrix and when to recommend each toolreferences/output-template.md -- Full workflow-automation.md structure to fill inreferences/diagram-and-estimation-standards.md -- Mermaid conventions and time/ROI estimation rulesreferences/intake.md.references/analysis-framework.md.references/analysis-framework.md.references/automation-design.md.references/tool-recommendations.md.references/diagram-and-estimation-standards.md.workflow-automation.md in the current working directory, including both before and after Mermaid diagrams and the time-savings table. See references/output-template.md and references/diagram-and-estimation-standards.md.Before delivering, verify:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→fail | 25,945 | 47,135 | +82% | 1 | 1 | 0% | 4,684 | 9,014 | +92% | 0 | 0 | — |
case-08 | fail→pass | 27,513 | 47,709 | +73% | 1 | 1 | 0% | 5,049 | 9,024 | +79% | 0 | 0 | — |
case-01 | pass→pass | 44,595 | 48,465 | +9% | 1 | 1 | 0% | 8,267 | 9,081 | +10% | 0 | 0 | — |
case-02 | fail→pass | 37,869 | 46,398 | +23% | 1 | 1 | 0% | 6,789 | 9,088 | +34% | 0 | 0 | — |
case-03 | fail→fail | 46,685 | 47,802 | +2% | 1 | 1 | 0% | 8,317 | 9,093 | +9% | 0 | 0 | — |
case-04 | fail→pass | 12,915 | 40,002 | +210% | 1 | 1 | 0% | 2,060 | 7,832 | +280% | 0 | 0 | — |
case-05 | fail→fail | 21,585 | 44,024 | +104% | 1 | 1 | 0% | 3,903 | 9,009 | +131% | 0 | 0 | — |
case-06 | fail→pass | 47,159 | 55,204 | +17% | 1 | 1 | 0% | 8,274 | 9,050 | +9% | 0 | 0 | — |
case-09 | fail→pass | 36,221 | 45,379 | +25% | 1 | 1 | 0% | 6,084 | 9,016 | +48% | 0 | 0 | — |
case-10 | pass→fail | 34,058 | 43,456 | +28% | 1 | 1 | 0% | 6,622 | 9,017 | +36% | 0 | 0 | — |
case-11 | fail→fail | 36,110 | 45,191 | +25% | 1 | 1 | 0% | 6,804 | 9,006 | +32% | 0 | 0 | — |
case-12 | pass→pass | 16,597 | 46,293 | +179% | 1 | 1 | 0% | 2,883 | 9,005 | +212% | 0 | 0 | — |
case-13 | fail→pass | 41,824 | 46,662 | +12% | 1 | 1 | 0% | 8,228 | 9,004 | +9% | 0 | 0 | — |
case-14 | pass→pass | 30,444 | 46,495 | +53% | 1 | 1 | 0% | 5,704 | 9,005 | +58% | 0 | 0 | — |
case-15 | fail→fail | 27,262 | 47,277 | +73% | 1 | 1 | 0% | 5,208 | 9,000 | +73% | 0 | 0 | — |
case-16 | fail→fail | 19,059 | 44,849 | +135% | 1 | 1 | 0% | 3,183 | 9,007 | +183% | 0 | 0 | — |
case-17 | fail→fail | 19,594 | 44,569 | +127% | 1 | 1 | 0% | 3,155 | 8,998 | +185% | 0 | 0 | — |
case-18 | pass→fail | 30,670 | 47,927 | +56% | 1 | 1 | 0% | 5,289 | 9,006 | +70% | 0 | 0 | — |
case-19 | pass→pass | 44,202 | 45,221 | +2% | 1 | 1 | 0% | 8,216 | 8,992 | +9% | 0 | 0 | — |
case-20 | pass→fail | 6,835 | 37,423 | +448% | 1 | 1 | 0% | 1,314 | 7,992 | +508% | 0 | 0 | — |
case-21 | pass→pass | 15,420 | 45,063 | +192% | 1 | 1 | 0% | 3,251 | 8,362 | +157% | 0 | 0 | — |
case-22 | pass→pass | 11,828 | 45,784 | +287% | 1 | 1 | 0% | 2,343 | 9,022 | +285% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
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.