Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generates professional Statements of Work from a project brief. Use when a user needs to create an SOW, scope a project, define deliverables and milestones, or produce a consulting engagement document.
.claude/skills/onewave-ai-sow-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 209% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 202% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 217% | 0% |
Generate complete, client-ready Statements of Work from a project brief, meeting the standards of Big Four consulting firms, top-tier agencies, and enterprise procurement. Produce polished documents ready for client review with minimal edits, never rough drafts or templates with blanks.
references/required-inputs.md -- inputs to gather and pre-generation client researchreferences/document-structure.md -- the 16-section SOW structure with templates for every sectionreferences/pricing-templates.md -- fixed-price, time-and-materials, and retainer pricing models (Section 11)references/legal-terms.md -- confidentiality, IP, warranties, liability, termination, and other legal clauses (Section 14)references/change-management.md -- change request and change order process (Section 12)references/risk-management.md -- risk register and escalation path (Section 13)references/required-inputs.md. If any required item is missing, ask for it explicitly. Do not guess at critical commercial terms.references/required-inputs.md to gather company overview, recent news, technology footprint, and regulatory environment. If research yields nothing, proceed on user-provided inputs and flag assumptions explicitly. Never fabricate company information.references/pricing-templates.md based on engagement type (default: fixed-price).references/document-structure.md, pulling Section 11 from pricing-templates, Section 12 from change-management, Section 13 from risk-management, and Section 14 from legal-terms. Replace every bracketed placeholder with real values from inputs and research. Leave brackets only where the user explicitly deferred. Mark gaps with [ACTION REQUIRED: ...].sow.md in the working directory (or a user-specified path).Verify before finalizing:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 43,694 | 6,830 | -84% | 1 | 1 | 0% | 7,478 | 1,217 | -84% | 0 | 0 | — |
case-02 | fail→fail | 49,151 | 9,056 | -82% | 1 | 1 | 0% | 8,262 | 1,615 | -80% | 0 | 0 | — |
case-03 | fail→fail | 34,535 | 45,277 | +31% | 1 | 1 | 0% | 6,508 | 9,117 | +40% | 0 | 0 | — |
case-04 | pass→pass | 25,733 | 42,814 | +66% | 1 | 1 | 0% | 4,899 | 9,089 | +86% | 0 | 0 | — |
case-05 | pass→fail | 19,861 | 14,090 | -29% | 1 | 1 | 0% | 3,237 | 3,307 | +2% | 0 | 0 | — |
case-06 | pass→pass | 12,057 | 10,555 | -12% | 1 | 1 | 0% | 1,979 | 2,560 | +29% | 0 | 0 | — |
case-07 | fail→pass | 15,390 | 15,114 | -2% | 1 | 1 | 0% | 2,795 | 3,533 | +26% | 0 | 0 | — |
case-08 | fail→fail | 18,060 | 45,874 | +154% | 1 | 1 | 0% | 3,255 | 9,083 | +179% | 0 | 0 | — |
case-09 | fail→pass | 16,348 | 45,192 | +176% | 1 | 1 | 0% | 2,941 | 9,090 | +209% | 0 | 0 | — |
case-10 | fail→pass | 42,740 | 54,190 | +27% | 1 | 1 | 0% | 6,529 | 9,080 | +39% | 0 | 0 | — |
case-11 | fail→fail | 18,062 | 9,731 | -46% | 1 | 1 | 0% | 3,015 | 1,439 | -52% | 0 | 0 | — |
case-12 | fail→pass | 16,441 | 54,321 | +230% | 1 | 1 | 0% | 3,008 | 9,093 | +202% | 0 | 0 | — |
case-13 | fail→pass | 15,759 | 49,915 | +217% | 1 | 1 | 0% | 2,868 | 9,093 | +217% | 0 | 0 | — |
case-14 | fail→fail | 35,442 | 46,678 | +32% | 1 | 1 | 0% | 6,588 | 9,078 | +38% | 0 | 0 | — |
case-15 | fail→fail | 18,941 | 10,473 | -45% | 1 | 1 | 0% | 2,880 | 1,682 | -42% | 0 | 0 | — |
case-16 | fail→fail | 18,476 | 46,150 | +150% | 1 | 1 | 0% | 3,191 | 9,080 | +185% | 0 | 0 | — |
case-17 | fail→fail | 24,690 | 46,009 | +86% | 1 | 1 | 0% | 3,992 | 9,075 | +127% | 0 | 0 | — |
case-18 | fail→pass | 19,174 | 19,271 | +1% | 1 | 1 | 0% | 2,556 | 4,005 | +57% | 0 | 0 | — |
case-19 | pass→pass | 14,217 | 55,971 | +294% | 1 | 1 | 0% | 2,621 | 9,087 | +247% | 0 | 0 | — |
case-20 | pass→fail | 15,562 | 9,035 | -42% | 1 | 1 | 0% | 2,681 | 1,452 | -46% | 0 | 0 | — |
case-21 | fail→fail | 30,838 | 9,855 | -68% | 1 | 1 | 0% | 4,331 | 1,565 | -64% | 0 | 0 | — |
case-22 | pass→pass | 14,453 | 54,916 | +280% | 1 | 1 | 0% | 2,735 | 9,089 | +232% | 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 16 counted toward the lift figure. The other 6 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 +18 percentage points is the difference between those two pass rates over the 16 comparable cases. 8 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.