Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manage a fundraise pipeline end-to-end with Finta. Use when running a fundraise, tracking investor conversations, managing deal rooms, or collecting commitments. Trigger with phrases like "finta fundraise", "finta pipeline management", "finta investor tracking", "run fundraise with finta".
.claude/skills/jeremylongshore-finta-core-workflow-a/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -43% | 0% |
End-to-end fundraise management with Finta: prospect investors, manage outreach, track meetings, handle due diligence, and close commitments.
Aurora AI analyzes your company profile and recommends investors based on:
Navigate to Investors > Discover and review AI-ranked suggestions.
Stage automation rules:
For each active conversation:
Track in Finta or export for custom analysis:
| Issue | Cause | Solution | |-------|-------|----------| | Emails not tracking | OAuth disconnected | Reconnect in Settings | | Deal room views not logging | Browser blocking | Share via direct email | | Payment link expired | Stripe session timeout | Generate new link | | Aurora suggestions poor | Incomplete profile | Complete all company fields |
For investor relations and updates, see finta-core-workflow-b.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,523 | 14,430 | -18% | 1 | 1 | 0% | 2,273 | 1,522 | -33% | 0 | 0 | — |
case-02 | fail→pass | 16,432 | 10,161 | -38% | 1 | 1 | 0% | 2,695 | 2,309 | -14% | 0 | 0 | — |
case-03 | fail→pass | 16,495 | 4,536 | -73% | 1 | 1 | 0% | 2,301 | 1,483 | -36% | 0 | 0 | — |
case-04 | fail→pass | 14,218 | 5,015 | -65% | 1 | 1 | 0% | 2,164 | 1,267 | -41% | 0 | 0 | — |
case-05 | fail→pass | 14,695 | 3,072 | -79% | 1 | 1 | 0% | 1,952 | 1,116 | -43% | 0 | 0 | — |
case-06 | fail→pass | 9,213 | 3,007 | -67% | 1 | 1 | 0% | 1,474 | 1,199 | -19% | 0 | 0 | — |
case-07 | pass→pass | 11,313 | 2,382 | -79% | 1 | 1 | 0% | 1,561 | 1,039 | -33% | 0 | 0 | — |
case-08 | pass→pass | 15,003 | 2,503 | -83% | 1 | 1 | 0% | 2,184 | 1,016 | -53% | 0 | 0 | — |
case-09 | fail→pass | 13,708 | 3,585 | -74% | 1 | 1 | 0% | 2,091 | 1,158 | -45% | 0 | 0 | — |
case-10 | fail→pass | 12,204 | 4,813 | -61% | 1 | 1 | 0% | 2,004 | 1,287 | -36% | 0 | 0 | — |
case-11 | pass→pass | 11,570 | 3,795 | -67% | 1 | 1 | 0% | 1,661 | 1,099 | -34% | 0 | 0 | — |
case-12 | fail→pass | 11,398 | 3,128 | -73% | 1 | 1 | 0% | 1,741 | 1,180 | -32% | 0 | 0 | — |
case-13 | pass→pass | 10,286 | 2,746 | -73% | 1 | 1 | 0% | 1,515 | 1,095 | -28% | 0 | 0 | — |
case-14 | pass→pass | 14,347 | 3,990 | -72% | 1 | 1 | 0% | 2,396 | 1,290 | -46% | 0 | 0 | — |
case-15 | fail→pass | 8,937 | 2,977 | -67% | 1 | 1 | 0% | 1,510 | 1,138 | -25% | 0 | 0 | — |
case-16 | pass→pass | 11,010 | 3,008 | -73% | 1 | 1 | 0% | 1,664 | 1,118 | -33% | 0 | 0 | — |
case-17 | pass→pass | 10,783 | 4,600 | -57% | 1 | 1 | 0% | 1,789 | 1,394 | -22% | 0 | 0 | — |
case-18 | pass→pass | 13,196 | 3,681 | -72% | 1 | 1 | 0% | 2,153 | 1,171 | -46% | 0 | 0 | — |
case-19 | pass→pass | 6,945 | 1,961 | -72% | 1 | 1 | 0% | 1,126 | 874 | -22% | 0 | 0 | — |
case-20 | fail→pass | 3,955 | 1,724 | -56% | 1 | 1 | 0% | 637 | 838 | +32% | 0 | 0 | — |
case-21 | fail→pass | 14,141 | 5,276 | -63% | 1 | 1 | 0% | 2,233 | 1,488 | -33% | 0 | 0 | — |
case-22 | fail→pass | 17,108 | 7,158 | -58% | 1 | 1 | 0% | 2,434 | 1,791 | -26% | 0 | 0 | — |
case-23 | fail→pass | 17,939 | 7,057 | -61% | 1 | 1 | 0% | 2,726 | 1,606 | -41% | 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 +61 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.