Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Set up your first fundraise pipeline in Finta with investors and deal stages. Use when starting a new fundraise, importing investor lists, or learning Finta's pipeline management features. Trigger with phrases like "finta hello world", "finta first pipeline", "start fundraise in finta", "finta quick start".
.claude/skills/jeremylongshore-finta-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -13% | 0% |
Create your first fundraise pipeline in Finta: add target investors, configure deal stages, and use Aurora AI for investor prospecting.
finta-install-auth setupManual Entry:
CSV Import:
csvName,Firm,Email,Check Size,Stage,Notes Jane Smith,Sequoia Capital,jane@sequoia.com,"$500K-$2M",Researching,Met at TechCrunch Bob Jones,a16z,bob@a16z.com,"$1M-$5M",Reaching Out,Intro from advisor
Aurora AI Prospecting:
Finta automatically moves investors through stages based on:
| Issue | Cause | Solution | |-------|-------|----------| | Investors not advancing | Auto-rules disabled | Check Settings > Automation | | Deal room link broken | Expired share | Regenerate link | | Metrics not populating | No financial integration | Connect Stripe/Mercury/Brex | | Aurora suggestions irrelevant | Insufficient company data | Complete company profile |
Proceed to finta-local-dev-loop for workflow automation setup.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,430 | 11,381 | -35% | 1 | 1 | 0% | 2,885 | 2,260 | -22% | 0 | 0 | — |
case-02 | fail→fail | 14,069 | 9,129 | -35% | 1 | 1 | 0% | 2,266 | 2,130 | -6% | 0 | 0 | — |
case-03 | fail→pass | 15,121 | 6,253 | -59% | 1 | 1 | 0% | 2,558 | 1,814 | -29% | 0 | 0 | — |
case-04 | pass→pass | 8,132 | 2,464 | -70% | 1 | 1 | 0% | 1,454 | 1,026 | -29% | 0 | 0 | — |
case-05 | fail→pass | 10,339 | 3,995 | -61% | 1 | 1 | 0% | 1,437 | 1,206 | -16% | 0 | 0 | — |
case-06 | fail→pass | 13,252 | 8,568 | -35% | 1 | 1 | 0% | 2,069 | 2,022 | -2% | 0 | 0 | — |
case-07 | pass→pass | 8,513 | 3,879 | -54% | 1 | 1 | 0% | 1,365 | 1,318 | -3% | 0 | 0 | — |
case-08 | pass→pass | 10,132 | 2,695 | -73% | 1 | 1 | 0% | 1,706 | 1,168 | -32% | 0 | 0 | — |
case-09 | fail→pass | 9,101 | 3,912 | -57% | 1 | 1 | 0% | 1,500 | 1,310 | -13% | 0 | 0 | — |
case-10 | fail→pass | 13,010 | 4,980 | -62% | 1 | 1 | 0% | 1,828 | 1,549 | -15% | 0 | 0 | — |
case-11 | fail→pass | 914,657 | 4,465 | -100% | 1 | 1 | 0% | 1,735 | 1,270 | -27% | 0 | 0 | — |
case-12 | pass→pass | 11,374 | 7,321 | -36% | 1 | 1 | 0% | 1,698 | 1,674 | -1% | 0 | 0 | — |
case-13 | pass→pass | 12,774 | 7,409 | -42% | 1 | 1 | 0% | 1,995 | 1,856 | -7% | 0 | 0 | — |
case-14 | fail→pass | 12,100 | 2,692 | -78% | 1 | 1 | 0% | 1,850 | 1,149 | -38% | 0 | 0 | — |
case-15 | pass→pass | 7,621 | 3,594 | -53% | 1 | 1 | 0% | 1,388 | 1,186 | -15% | 0 | 0 | — |
case-16 | fail→pass | 14,579 | 4,711 | -68% | 1 | 1 | 0% | 2,052 | 1,496 | -27% | 0 | 0 | — |
case-17 | fail→pass | 11,220 | 2,671 | -76% | 1 | 1 | 0% | 1,945 | 1,212 | -38% | 0 | 0 | — |
case-18 | pass→pass | 10,462 | 3,745 | -64% | 1 | 1 | 0% | 1,624 | 1,295 | -20% | 0 | 0 | — |
case-19 | pass→pass | 9,970 | 4,997 | -50% | 1 | 1 | 0% | 1,536 | 1,465 | -5% | 0 | 0 | — |
case-20 | fail→pass | 15,627 | 4,949 | -68% | 1 | 1 | 0% | 2,248 | 1,446 | -36% | 0 | 0 | — |
case-21 | fail→fail | 18,723 | 16,615 | -11% | 1 | 1 | 0% | 3,241 | 3,379 | +4% | 0 | 0 | — |
case-22 | fail→fail | 17,638 | 8,332 | -53% | 1 | 1 | 0% | 2,872 | 2,034 | -29% | 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 +50 percentage points is the difference between those two pass rates over the 22 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.