Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manage ongoing investor relations and updates with Finta. Use when sending investor updates, tracking cap table changes, or maintaining LP relationships post-close. Trigger with phrases like "finta investor updates", "finta LP management", "finta post-close", "finta investor relations".
.claude/skills/jeremylongshore-finta-core-workflow-b/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -44% | 0% |
Post-fundraise investor management: send periodic updates, share metrics, manage cap table, and maintain relationships for future rounds.
Subject: [Company] Monthly Update - March 2026
Key Metrics:
- MRR: $X (up Y% MoM)
- ARR: $X
- Burn Rate: $X/month
- Runway: X months
- Headcount: X
Highlights:
- [Achievement 1]
- [Achievement 2]
Challenges:
- [Challenge and plan to address]
Asks:
- Introductions to [specific companies/people]
- Feedback on [specific topic]Finta's network feature identifies 2nd-degree connections:
For troubleshooting, see finta-common-errors.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,045 | 13,198 | -6% | 1 | 1 | 0% | 2,431 | 1,571 | -35% | 0 | 0 | — |
case-02 | fail→pass | 10,029 | 3,393 | -66% | 1 | 1 | 0% | 1,457 | 917 | -37% | 0 | 0 | — |
case-03 | pass→pass | 15,483 | 5,329 | -66% | 1 | 1 | 0% | 2,688 | 1,349 | -50% | 0 | 0 | — |
case-04 | pass→pass | 11,326 | 3,730 | -67% | 1 | 1 | 0% | 1,664 | 955 | -43% | 0 | 0 | — |
case-05 | pass→pass | 9,231 | 3,742 | -59% | 1 | 1 | 0% | 1,553 | 980 | -37% | 0 | 0 | — |
case-06 | pass→pass | 6,862 | 2,107 | -69% | 1 | 1 | 0% | 1,213 | 756 | -38% | 0 | 0 | — |
case-07 | pass→pass | 5,895 | 2,199 | -63% | 1 | 1 | 0% | 1,060 | 770 | -27% | 0 | 0 | — |
case-08 | pass→pass | 9,185 | 2,365 | -74% | 1 | 1 | 0% | 1,474 | 829 | -44% | 0 | 0 | — |
case-09 | pass→pass | 6,845 | 2,177 | -68% | 1 | 1 | 0% | 1,121 | 783 | -30% | 0 | 0 | — |
case-10 | pass→pass | 8,725 | 2,196 | -75% | 1 | 1 | 0% | 1,201 | 806 | -33% | 0 | 0 | — |
case-11 | fail→pass | 7,581 | 1,655 | -78% | 1 | 1 | 0% | 1,236 | 706 | -43% | 0 | 0 | — |
case-12 | pass→pass | 7,241 | 2,424 | -67% | 1 | 1 | 0% | 1,214 | 752 | -38% | 0 | 0 | — |
case-13 | pass→pass | 124,796 | 2,643 | -98% | 1 | 1 | 0% | 1,617 | 881 | -46% | 0 | 0 | — |
case-14 | fail→pass | 9,555 | 4,035 | -58% | 1 | 1 | 0% | 1,495 | 956 | -36% | 0 | 0 | — |
case-15 | pass→pass | 15,136 | 7,827 | -48% | 1 | 1 | 0% | 2,001 | 1,438 | -28% | 0 | 0 | — |
case-16 | fail→pass | 6,827 | 1,462 | -79% | 1 | 1 | 0% | 1,123 | 629 | -44% | 0 | 0 | — |
case-17 | fail→fail | 6,725 | 2,039 | -70% | 1 | 1 | 0% | 1,149 | 762 | -34% | 0 | 0 | — |
case-18 | pass→pass | 5,335 | 1,468 | -72% | 1 | 1 | 0% | 902 | 681 | -25% | 0 | 0 | — |
case-19 | fail→pass | 11,302 | 4,655 | -59% | 1 | 1 | 0% | 1,772 | 1,074 | -39% | 0 | 0 | — |
case-20 | fail→pass | 15,027 | 8,888 | -41% | 1 | 1 | 0% | 2,533 | 1,847 | -27% | 0 | 0 | — |
case-21 | fail→fail | 12,066 | 8,414 | -30% | 1 | 1 | 0% | 1,933 | 1,831 | -5% | 0 | 0 | — |
case-22 | fail→pass | 16,149 | 9,430 | -42% | 1 | 1 | 0% | 2,957 | 1,684 | -43% | 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 +36 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.