Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Simulate the VC partner meeting that discusses your pitch after you leave the room — four partner archetypes debate, then write the internal verdict memo. Use when asked how will VCs discuss my pitch, simulate the partner meeting, stress-test my fundraise, or what happens after the pitch. Produces the meeting transcript, the internal fund/pass/track memo, and a debrief listing which objections are fixable before the real meeting.
.claude/skills/mohitagw15856-vc-partner-meeting/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -1% | 0% |
The most important meeting of your fundraise is one you're not in. This skill runs it early: four partners who just watched your pitch debate it the way funds actually do — pattern-matching, fund math, and all — then commit a verdict to the internal memo.
Ask for these if not provided:
Each speaks at least twice; they must disagree somewhere — real partner meetings are arguments:
| Partner | What they weigh | Their failure mode (include it) | |---|---|---| | The Champion | Why this could be huge; founder quality | Falls in love, discounts risk | | The Skeptic | Why this dies: competition, moat, timing | Kills things that later win | | The Pattern-Matcher | "This looks like X in 2021" — comps, cautionary tales | Fights the last war | | The Fund-Math Partner | Can THIS check return the fund? Ownership, entry price, follow-on reserve | Passes on great-but-small |
Verdicts: FUND (term sheet path) · TRACK (specific milestone named — "come back at $1M ARR") · PASS (real reason, not the polite one).
Ground every argument in the supplied facts; where the pitch is silent, the partners should notice the silence — that is realistic — rather than invent numbers.
> Simulation — a plausible adversarial reading, not a prediction or investment advice.
Natural discussion, 12–20 exchanges. Interruptions, references to the deck's actual numbers, at least one genuine disagreement that doesn't fully resolve.]
Verdict: FUND / TRACK / PASS One-line thesis or anti-thesis: … What we'd need to believe: 3 bullets Deal terms discussed: ownership target, price reaction If TRACK: the named milestone. If PASS: the real reason vs. what the associate will email the founder.
| Objection raised | Fixable before the real meeting? | How | |---|---|---|
One paragraph: the single strongest move before pitching for real.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→fail | 37,243 | 31,609 | -15% | 1 | 1 | 0% | 3,167 | 4,596 | +45% | 0 | 0 | — |
case-01 | fail→fail | 42,187 | 42,970 | +2% | 1 | 1 | 0% | 5,755 | 5,853 | +2% | 0 | 0 | — |
case-02 | fail→pass | 55,525 | 33,501 | -40% | 1 | 1 | 0% | 7,251 | 5,221 | -28% | 0 | 0 | — |
case-03 | fail→fail | 43,596 | 40,917 | -6% | 1 | 1 | 0% | 5,124 | 5,523 | +8% | 0 | 0 | — |
case-18 | pass→pass | 27,827 | 29,884 | +7% | 1 | 1 | 0% | 3,236 | 4,748 | +47% | 0 | 0 | — |
case-04 | pass→pass | 25,680 | 33,828 | +32% | 1 | 1 | 0% | 4,000 | 5,917 | +48% | 0 | 0 | — |
case-05 | pass→pass | 22,186 | 24,537 | +11% | 1 | 1 | 0% | 2,297 | 4,207 | +83% | 0 | 0 | — |
case-06 | pass→pass | 16,602 | 23,900 | +44% | 1 | 1 | 0% | 1,535 | 3,222 | +110% | 0 | 0 | — |
case-07 | pass→pass | 27,527 | 31,716 | +15% | 1 | 1 | 0% | 3,025 | 4,548 | +50% | 0 | 0 | — |
case-19 | fail→pass | 29,762 | 31,282 | +5% | 1 | 1 | 0% | 3,287 | 4,311 | +31% | 0 | 0 | — |
case-08 | pass→pass | 29,944 | 49,544 | +65% | 1 | 1 | 0% | 3,834 | 6,791 | +77% | 0 | 0 | — |
case-09 | fail→pass | 39,696 | 31,751 | -20% | 1 | 1 | 0% | 4,827 | 5,194 | +8% | 0 | 0 | — |
case-10 | pass→pass | 26,991 | 36,106 | +34% | 1 | 1 | 0% | 3,002 | 4,748 | +58% | 0 | 0 | — |
case-11 | fail→fail | 28,184 | 38,246 | +36% | 1 | 1 | 0% | 3,783 | 5,434 | +44% | 0 | 0 | — |
case-12 | fail→pass | 27,445 | 21,589 | -21% | 1 | 1 | 0% | 3,172 | 3,151 | -1% | 0 | 0 | — |
case-13 | pass→fail | 26,036 | 18,307 | -30% | 1 | 1 | 0% | 2,783 | 3,023 | +9% | 0 | 0 | — |
case-14 | fail→pass | 34,114 | 40,184 | +18% | 1 | 1 | 0% | 5,151 | 5,119 | -1% | 0 | 0 | — |
case-15 | pass→pass | 28,564 | 32,730 | +15% | 1 | 1 | 0% | 3,328 | 4,804 | +44% | 0 | 0 | — |
case-16 | pass→pass | 46,090 | 40,079 | -13% | 1 | 1 | 0% | 3,337 | 6,226 | +87% | 0 | 0 | — |
case-20 | fail→fail | 24,716 | 13,273 | -46% | 1 | 1 | 0% | 2,977 | 2,126 | -29% | 0 | 0 | — |
case-21 | fail→pass | 20,225 | 15,746 | -22% | 1 | 1 | 0% | 2,227 | 2,386 | +7% | 0 | 0 | — |
case-22 | pass→pass | 23,396 | 35,342 | +51% | 1 | 1 | 0% | 3,176 | 6,071 | +91% | 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 +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.