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/affaan-m-investor-outreach/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -1% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
撰写简短、个性化且易于采取行动的投资者沟通内容。
参考以下一项或多项：
如果缺少相关背景信息，请询问或说明草稿是等待个性化的模板。
默认节奏：
之后除非用户要求更长的跟进序列，否则不再继续提醒。
为介绍人提供便利：
包含：
在交付前检查：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | pass→pass | 9,437 | 6,118 | -35% | 1 | 1 | 0% | 1,551 | 1,532 | -1% | 0 | 0 | — |
case-04 | pass→pass | 8,721 | 5,517 | -37% | 1 | 1 | 0% | 1,480 | 1,434 | -3% | 0 | 0 | — |
case-01 | fail→pass | 14,967 | 11,346 | -24% | 1 | 1 | 0% | 2,114 | 2,282 | +8% | 0 | 0 | — |
case-02 | fail→pass | 9,920 | 7,326 | -26% | 1 | 1 | 0% | 1,728 | 1,764 | +2% | 0 | 0 | — |
case-05 | pass→pass | 11,433 | 6,426 | -44% | 1 | 1 | 0% | 1,880 | 1,593 | -15% | 0 | 0 | — |
case-06 | pass→pass | 7,746 | 7,092 | -8% | 1 | 1 | 0% | 1,303 | 1,548 | +19% | 0 | 0 | — |
case-07 | pass→pass | 71,260 | 7,298 | -90% | 1 | 1 | 0% | 1,606 | 1,826 | +14% | 0 | 0 | — |
case-08 | pass→pass | 12,692 | 10,821 | -15% | 1 | 1 | 0% | 2,020 | 2,273 | +13% | 0 | 0 | — |
case-09 | fail→fail | 7,449 | 8,552 | +15% | 1 | 1 | 0% | 1,251 | 1,861 | +49% | 0 | 0 | — |
case-10 | pass→pass | 13,004 | 11,516 | -11% | 1 | 1 | 0% | 1,911 | 2,162 | +13% | 0 | 0 | — |
case-11 | pass→pass | 12,864 | 8,649 | -33% | 1 | 1 | 0% | 1,922 | 1,907 | -1% | 0 | 0 | — |
case-12 | pass→pass | 12,182 | 8,830 | -28% | 1 | 1 | 0% | 1,984 | 1,824 | -8% | 0 | 0 | — |
case-13 | pass→pass | 12,439 | 7,728 | -38% | 1 | 1 | 0% | 1,701 | 1,776 | +4% | 0 | 0 | — |
case-14 | fail→fail | 8,175 | 9,524 | +17% | 1 | 1 | 0% | 1,248 | 1,864 | +49% | 0 | 0 | — |
case-20 | pass→pass | 15,353 | 14,317 | -7% | 1 | 1 | 0% | 2,533 | 2,716 | +7% | 0 | 0 | — |
case-15 | pass→pass | 9,913 | 10,041 | +1% | 1 | 1 | 0% | 1,497 | 1,626 | +9% | 0 | 0 | — |
case-16 | pass→pass | 8,340 | 10,437 | +25% | 1 | 1 | 0% | 1,296 | 2,197 | +70% | 0 | 0 | — |
case-17 | fail→pass | 8,575 | 5,922 | -31% | 1 | 1 | 0% | 1,392 | 1,464 | +5% | 0 | 0 | — |
case-18 | pass→pass | 9,223 | 4,673 | -49% | 1 | 1 | 0% | 1,315 | 1,239 | -6% | 0 | 0 | — |
case-19 | fail→fail | 12,290 | 8,579 | -30% | 1 | 1 | 0% | 1,712 | 1,831 | +7% | 0 | 0 | — |
case-21 | pass→pass | 14,039 | 14,020 | -0% | 1 | 1 | 0% | 2,524 | 2,712 | +7% | 0 | 0 | — |
case-22 | pass→pass | 4,131 | 3,318 | -20% | 1 | 1 | 0% | 797 | 1,125 | +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. 22 cases were attempted. The headline lift of +14 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.