Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Finta pipeline events with Zapier and email triggers. Use when setting up notifications for investor responses, automating follow-up reminders, or syncing events to other tools. Trigger with phrases like "finta automation", "finta notifications", "finta pipeline events", "finta zapier".
.claude/skills/jeremylongshore-finta-webhooks-events/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -55% | 0% |
Finta supports event automation through its built-in automation rules and Zapier integration. Pipeline stage changes, investor replies, and deal room views can trigger external actions.
Configure in Settings > Automation:
Available triggers:
Example Zap: Finta stage change -> Slack message + Google Sheets row
pythonimport pandas as pd from datetime import datetime, timedelta def get_followup_reminders(export_path: str, days: int = 5) -> list: df = pd.read_csv(export_path) df["Last Contact"] = pd.to_datetime(df["Last Contact"]) cutoff = datetime.now() - timedelta(days=days) overdue = df[ (df["Stage"].isin(["Reaching Out", "Follow-up"])) & (df["Last Contact"] < cutoff) ] return overdue[["Name", "Firm", "Email", "Last Contact", "Stage"]].to_dict("records")
For performance, see finta-performance-tuning.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 30,150 | 5,760 | -81% | 1 | 1 | 0% | 2,660 | 1,087 | -59% | 0 | 0 | — |
case-02 | fail→fail | 22,601 | 6,876 | -70% | 1 | 1 | 0% | 3,547 | 1,594 | -55% | 0 | 0 | — |
case-03 | fail→fail | 18,261 | 9,646 | -47% | 1 | 1 | 0% | 3,117 | 2,159 | -31% | 0 | 0 | — |
case-04 | fail→fail | 17,035 | 7,679 | -55% | 1 | 1 | 0% | 2,702 | 1,591 | -41% | 0 | 0 | — |
case-05 | pass→pass | 128,230 | 6,888 | -95% | 1 | 1 | 0% | 2,463 | 1,622 | -34% | 0 | 0 | — |
case-06 | pass→pass | 17,934 | 4,829 | -73% | 1 | 1 | 0% | 2,892 | 1,056 | -63% | 0 | 0 | — |
case-07 | fail→pass | 7,598 | 3,705 | -51% | 1 | 1 | 0% | 1,280 | 955 | -25% | 0 | 0 | — |
case-08 | pass→pass | 8,007 | 2,282 | -71% | 1 | 1 | 0% | 1,327 | 751 | -43% | 0 | 0 | — |
case-09 | pass→pass | 9,221 | 1,617 | -82% | 1 | 1 | 0% | 1,273 | 642 | -50% | 0 | 0 | — |
case-10 | pass→pass | 6,722 | 2,345 | -65% | 1 | 1 | 0% | 926 | 763 | -18% | 0 | 0 | — |
case-11 | fail→pass | 7,865 | 1,809 | -77% | 1 | 1 | 0% | 1,184 | 596 | -50% | 0 | 0 | — |
case-12 | fail→pass | 5,293 | 2,004 | -62% | 1 | 1 | 0% | 924 | 731 | -21% | 0 | 0 | — |
case-13 | fail→pass | 9,648 | 2,250 | -77% | 1 | 1 | 0% | 1,558 | 703 | -55% | 0 | 0 | — |
case-14 | fail→pass | 6,072 | 1,989 | -67% | 1 | 1 | 0% | 966 | 651 | -33% | 0 | 0 | — |
case-15 | fail→pass | 8,726 | 2,055 | -76% | 1 | 1 | 0% | 1,470 | 672 | -54% | 0 | 0 | — |
case-16 | pass→pass | 16,021 | 7,110 | -56% | 1 | 1 | 0% | 2,690 | 1,668 | -38% | 0 | 0 | — |
case-17 | fail→pass | 18,746 | 2,215 | -88% | 1 | 1 | 0% | 1,082 | 776 | -28% | 0 | 0 | — |
case-18 | pass→pass | 7,695 | 2,321 | -70% | 1 | 1 | 0% | 1,330 | 743 | -44% | 0 | 0 | — |
case-19 | fail→pass | 12,824 | 2,241 | -83% | 1 | 1 | 0% | 2,057 | 755 | -63% | 0 | 0 | — |
case-20 | pass→pass | 11,795 | 3,711 | -69% | 1 | 1 | 0% | 2,221 | 1,076 | -52% | 0 | 0 | — |
case-21 | fail→pass | 4,467 | 2,692 | -40% | 1 | 1 | 0% | 700 | 842 | +20% | 0 | 0 | — |
case-22 | pass→pass | 5,186 | 2,548 | -51% | 1 | 1 | 0% | 675 | 849 | +26% | 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, and 21 counted toward the lift figure. The other 1 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 +45 percentage points is the difference between those two pass rates over the 21 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.