Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
.claude/skills/loulanyue-investor-outreach/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 9% | 0% |
Write investor communication that is short, personalized, and easy to act on.
Reference one or more of:
If that context is missing, ask for it or state that the draft is a template awaiting personalization.
Default:
Do not keep nudging after that unless the user wants a longer sequence.
Make life easy for the connector:
Include:
Before delivering:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→pass | 11,923 | 9,024 | -24% | 1 | 1 | 0% | 1,783 | 1,896 | +6% | 0 | 0 | — |
case-01 | fail→pass | 10,179 | 6,924 | -32% | 1 | 1 | 0% | 1,669 | 1,729 | +4% | 0 | 0 | — |
case-02 | fail→pass | 11,776 | 8,548 | -27% | 1 | 1 | 0% | 1,777 | 1,782 | +0% | 0 | 0 | — |
case-03 | pass→pass | 11,203 | 7,097 | -37% | 1 | 1 | 0% | 1,657 | 1,636 | -1% | 0 | 0 | — |
case-04 | fail→pass | 10,383 | 6,258 | -40% | 1 | 1 | 0% | 1,595 | 1,444 | -9% | 0 | 0 | — |
case-05 | pass→pass | 12,922 | 7,698 | -40% | 1 | 1 | 0% | 1,935 | 1,666 | -14% | 0 | 0 | — |
case-06 | pass→pass | 12,200 | 7,868 | -36% | 1 | 1 | 0% | 1,832 | 1,637 | -11% | 0 | 0 | — |
case-07 | fail→pass | 9,563 | 7,131 | -25% | 1 | 1 | 0% | 1,483 | 1,618 | +9% | 0 | 0 | — |
case-08 | pass→pass | 9,091 | 5,971 | -34% | 1 | 1 | 0% | 1,453 | 1,510 | +4% | 0 | 0 | — |
case-10 | pass→pass | 12,105 | 9,304 | -23% | 1 | 1 | 0% | 1,749 | 1,953 | +12% | 0 | 0 | — |
case-11 | fail→pass | 16,712 | 10,378 | -38% | 1 | 1 | 0% | 2,498 | 2,149 | -14% | 0 | 0 | — |
case-12 | fail→pass | 10,147 | 6,136 | -40% | 1 | 1 | 0% | 1,590 | 1,407 | -12% | 0 | 0 | — |
case-13 | pass→pass | 10,022 | 5,661 | -44% | 1 | 1 | 0% | 1,540 | 1,412 | -8% | 0 | 0 | — |
case-14 | fail→pass | 15,753 | 13,185 | -16% | 1 | 1 | 0% | 2,185 | 2,416 | +11% | 0 | 0 | — |
case-15 | pass→pass | 8,482 | 5,850 | -31% | 1 | 1 | 0% | 1,275 | 1,448 | +14% | 0 | 0 | — |
case-16 | fail→pass | 13,129 | 8,834 | -33% | 1 | 1 | 0% | 1,855 | 1,733 | -7% | 0 | 0 | — |
case-17 | pass→pass | 9,519 | 5,588 | -41% | 1 | 1 | 0% | 1,423 | 1,354 | -5% | 0 | 0 | — |
case-18 | pass→fail | 11,188 | 7,859 | -30% | 1 | 1 | 0% | 1,616 | 1,624 | +0% | 0 | 0 | — |
case-19 | pass→pass | 15,993 | 6,341 | -60% | 1 | 1 | 0% | 1,661 | 1,476 | -11% | 0 | 0 | — |
case-20 | pass→pass | 13,347 | 9,499 | -29% | 1 | 1 | 0% | 2,088 | 1,949 | -7% | 0 | 0 | — |
case-21 | pass→pass | 19,523 | 12,302 | -37% | 1 | 1 | 0% | 3,095 | 2,386 | -23% | 0 | 0 | — |
case-22 | pass→pass | 16,163 | 11,866 | -27% | 1 | 1 | 0% | 2,687 | 2,327 | -13% | 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. 1 case got worse with the skill loaded, and it is 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.