Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Score a pitch deck's structure and content against YC, Sequoia, and a16z heuristics. Use before sending a deck to investors, practicing a pitch, or reviewing a seed or Series A fundraising deck.
.claude/skills/borghei-pitch-deck-reviewer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -23% | 0% |
Score a pitch deck's structure against the YC / Sequoia / a16z heuristics.
> Note: This evaluates structure, not content quality. A perfectly-structured deck for a bad business is still a bad pitch. But a poorly-structured deck for a great business often gets passed.
pitch deck, pitch, fundraise, fundraising, seed deck, Series A deck, investor deck, slide deck, YC, Y Combinator, Sequoia, a16z
Before scoring the deck, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--stage flag) and what counts as a gapStop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
deck_summary.md (slide number + title + 1-2 sentences of content)python scripts/deck_structure_scorer.py deck_summary.mddeck_summary.mddocuments/pptx-toolkit/ for actual pptx auditTime Estimate: 1-2 hours per major deck iteration.
references/pitch_deck_heuristics.mdTime Estimate: 1-2 weeks for first complete draft.
Reads a markdown file describing the deck slide-by-slide and scores it against required slides per stage.
bashpython scripts/deck_structure_scorer.py deck_summary.md python scripts/deck_structure_scorer.py deck_summary.md --json # For Series A python scripts/deck_structure_scorer.py deck_summary.md --stage series-a
Stages: seed (default), series-a.
references/pitch_deck_heuristics.md — YC, Sequoia, a16z deck structure heuristics; common mistakes; stage differencesassets/deck_summary_template.md — Slide-by-slide summary template| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | pass→pass | 21,332 | 16,240 | -24% | 1 | 1 | 0% | 3,252 | 3,710 | +14% | 0 | 0 | — |
case-03 | pass→pass | 8,475 | 6,358 | -25% | 1 | 1 | 0% | 1,326 | 1,831 | +38% | 0 | 0 | — |
case-04 | pass→pass | 18,223 | 19,852 | +9% | 1 | 1 | 0% | 3,846 | 4,363 | +13% | 0 | 0 | — |
case-01 | fail→pass | 15,377 | 10,403 | -32% | 1 | 1 | 0% | 2,447 | 2,682 | +10% | 0 | 0 | — |
case-05 | fail→pass | 5,720 | 3,657 | -36% | 1 | 1 | 0% | 798 | 1,278 | +60% | 0 | 0 | — |
case-06 | pass→pass | 4,485 | 2,670 | -40% | 1 | 1 | 0% | 652 | 1,176 | +80% | 0 | 0 | — |
case-07 | pass→pass | 8,098 | 1,945 | -76% | 1 | 1 | 0% | 1,300 | 1,142 | -12% | 0 | 0 | — |
case-08 | pass→pass | 13,046 | 9,757 | -25% | 1 | 1 | 0% | 1,938 | 2,380 | +23% | 0 | 0 | — |
case-09 | fail→pass | 10,176 | 9,797 | -4% | 1 | 1 | 0% | 1,666 | 2,431 | +46% | 0 | 0 | — |
case-10 | pass→pass | 8,886 | 8,270 | -7% | 1 | 1 | 0% | 1,420 | 2,109 | +49% | 0 | 0 | — |
case-11 | pass→pass | 7,094 | 7,580 | +7% | 1 | 1 | 0% | 1,156 | 2,141 | +85% | 0 | 0 | — |
case-12 | pass→pass | 23,749 | 10,408 | -56% | 1 | 1 | 0% | 2,025 | 2,333 | +15% | 0 | 0 | — |
case-13 | fail→pass | 13,922 | 6,996 | -50% | 1 | 1 | 0% | 2,120 | 2,009 | -5% | 0 | 0 | — |
case-14 | pass→pass | 17,175 | 10,124 | -41% | 1 | 1 | 0% | 2,416 | 2,495 | +3% | 0 | 0 | — |
case-15 | pass→pass | 10,721 | 7,970 | -26% | 1 | 1 | 0% | 1,573 | 2,039 | +30% | 0 | 0 | — |
case-16 | pass→pass | 13,400 | 12,130 | -9% | 1 | 1 | 0% | 2,061 | 2,670 | +30% | 0 | 0 | — |
case-17 | pass→pass | 17,636 | 13,719 | -22% | 1 | 1 | 0% | 2,460 | 2,824 | +15% | 0 | 0 | — |
case-18 | pass→pass | 16,006 | 11,342 | -29% | 1 | 1 | 0% | 2,386 | 2,569 | +8% | 0 | 0 | — |
case-19 | fail→pass | 8,791 | 1,684 | -81% | 1 | 1 | 0% | 1,376 | 1,059 | -23% | 0 | 0 | — |
case-20 | fail→pass | 6,666 | 1,631 | -76% | 1 | 1 | 0% | 958 | 1,117 | +17% | 0 | 0 | — |
case-21 | fail→pass | 13,157 | 3,650 | -72% | 1 | 1 | 0% | 2,087 | 1,410 | -32% | 0 | 0 | — |
case-22 | pass→pass | 8,329 | 5,782 | -31% | 1 | 1 | 0% | 1,270 | 1,651 | +30% | 0 | 0 | — |
case-23 | fail→pass | 11,818 | 2,198 | -81% | 1 | 1 | 0% | 1,749 | 1,170 | -33% | 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. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 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.