Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Reviews pitch decks and investor presentations. Reads slide content, evaluates narrative flow, problem/solution clarity, market sizing, competitive positioning, financial projections, team credibility, and ask clarity. Generates a scored pitch-review.md with slide-by-slide feedback, overall score, top improvements, investor objection predictions, and comparisons to successful decks. Use when reviewing fundraising materials, investor decks, or pitch presentations.
.claude/skills/onewave-ai-pitch-deck-reviewer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -63% | 0% |
| case-16 | ✓→✗ | ▼ Worse | 116% | 0% |
Review a pitch deck with VC-grade rigor and produce a scored, actionable pitch-review.md.
references/evaluation-framework.md -- The 8 scored dimensions, weights, red flags, scoring guides, design notes, and overall-score calculation.references/objections-and-benchmarks.md -- Investor objection categories and the canonical successful-deck benchmarks.references/output-template.md -- The exact pitch-review.md structure to generate.pages parameter), PowerPoint .pptx (invoke the pptx skill or Read), Google Slides links (WebFetch if public), images PNG/JPG (Read to inspect visually), markdown/text descriptions, and directories of slide images (Glob to enumerate, then Read each). For .pen files, state that they cannot be read directly.references/evaluation-framework.md. Score each 1-10 with specific evidence from the deck, then compute the weighted overall score and assign the grade label.references/objections-and-benchmarks.md, each with severity, trigger, suggested verbal response, and deck fix.references/objections-and-benchmarks.md; name where this deck is stronger, weaker, and what to borrow.pitch-review.md per references/output-template.md. Write the executive summary last. Save it beside the source deck (or the working directory). Show the overall-score math.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,694 | 8,982 | +58% | 1 | 1 | 0% | 283 | 1,053 | +272% | 0 | 0 | — |
case-02 | fail→fail | 9,978 | 2,924 | -71% | 1 | 1 | 0% | 1,697 | 1,021 | -40% | 0 | 0 | — |
case-03 | fail→fail | 33,072 | 18,993 | -43% | 1 | 1 | 0% | 6,226 | 1,094 | -82% | 0 | 0 | — |
case-04 | pass→fail | 16,522 | 4,447 | -73% | 1 | 1 | 0% | 2,766 | 1,026 | -63% | 0 | 0 | — |
case-05 | pass→pass | 10,521 | 5,462 | -48% | 1 | 1 | 0% | 1,602 | 1,610 | +0% | 0 | 0 | — |
case-06 | fail→fail | 7,792 | 4,566 | -41% | 1 | 1 | 0% | 1,097 | 1,063 | -3% | 0 | 0 | — |
case-07 | pass→pass | 16,165 | 11,993 | -26% | 1 | 1 | 0% | 2,512 | 2,513 | +0% | 0 | 0 | — |
case-08 | fail→fail | 7,659 | 4,530 | -41% | 1 | 1 | 0% | 1,182 | 991 | -16% | 0 | 0 | — |
case-09 | fail→fail | 5,310 | 7,778 | +46% | 1 | 1 | 0% | 922 | 2,091 | +127% | 0 | 0 | — |
case-10 | fail→fail | 5,885 | 3,630 | -38% | 1 | 1 | 0% | 1,062 | 1,074 | +1% | 0 | 0 | — |
case-11 | fail→fail | 6,719 | 1,693 | -75% | 1 | 1 | 0% | 1,210 | 1,068 | -12% | 0 | 0 | — |
case-12 | fail→fail | 4,179 | 1,250 | -70% | 1 | 1 | 0% | 651 | 987 | +52% | 0 | 0 | — |
case-13 | fail→fail | 7,722 | 3,550 | -54% | 1 | 1 | 0% | 1,374 | 1,411 | +3% | 0 | 0 | — |
case-14 | fail→pass | 11,778 | 4,986 | -58% | 1 | 1 | 0% | 1,956 | 1,395 | -29% | 0 | 0 | — |
case-15 | fail→fail | 7,874 | 4,883 | -38% | 1 | 1 | 0% | 1,225 | 1,621 | +32% | 0 | 0 | — |
case-16 | pass→fail | 3,133 | 2,433 | -22% | 1 | 1 | 0% | 537 | 1,160 | +116% | 0 | 0 | — |
case-17 | fail→fail | 5,647 | 5,616 | -1% | 1 | 1 | 0% | 988 | 1,275 | +29% | 0 | 0 | — |
case-18 | fail→pass | 8,605 | 6,558 | -24% | 1 | 1 | 0% | 1,365 | 1,896 | +39% | 0 | 0 | — |
case-19 | fail→fail | 6,557 | 4,416 | -33% | 1 | 1 | 0% | 1,007 | 985 | -2% | 0 | 0 | — |
case-20 | fail→pass | 10,353 | 3,350 | -68% | 1 | 1 | 0% | 1,657 | 1,370 | -17% | 0 | 0 | — |
case-21 | pass→pass | 13,638 | 15,019 | +10% | 1 | 1 | 0% | 1,826 | 3,454 | +89% | 0 | 0 | — |
case-22 | pass→fail | 25,031 | 3,808 | -85% | 1 | 1 | 0% | 6,178 | 1,011 | -84% | 0 | 0 | — |
case-23 | pass→pass | 20,322 | 17,421 | -14% | 1 | 1 | 0% | 3,452 | 4,011 | +16% | 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. 23 cases were attempted, and 14 counted toward the lift figure. The other 9 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 14 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.