Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
.claude/skills/affaan-m-investor-materials/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 11% | 0% |
构建面向投资者的材料，要求一致、可信且易于辩护。
所有投资者材料必须彼此一致。
在撰写前创建或确认单一事实来源：
如果出现冲突的数字，请停止起草并解决它们。
推荐流程：
如果用户想要一个基于网页的演讲稿，请将此技能与 frontend-slides 配对使用。
包含：
在交付前：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 18,931 | 19,058 | +1% | 1 | 1 | 0% | 3,042 | 3,896 | +28% | 0 | 0 | — |
case-01 | fail→fail | 27,018 | 25,246 | -7% | 1 | 1 | 0% | 4,593 | 5,246 | +14% | 0 | 0 | — |
case-02 | fail→pass | 16,674 | 15,851 | -5% | 1 | 1 | 0% | 2,569 | 3,268 | +27% | 0 | 0 | — |
case-03 | fail→pass | 19,040 | 21,392 | +12% | 1 | 1 | 0% | 3,254 | 3,899 | +20% | 0 | 0 | — |
case-04 | fail→pass | 20,875 | 22,277 | +7% | 1 | 1 | 0% | 3,413 | 4,221 | +24% | 0 | 0 | — |
case-05 | fail→fail | 20,233 | 19,470 | -4% | 1 | 1 | 0% | 3,403 | 3,603 | +6% | 0 | 0 | — |
case-06 | fail→pass | 14,956 | 15,750 | +5% | 1 | 1 | 0% | 2,245 | 2,881 | +28% | 0 | 0 | — |
case-07 | pass→fail | 13,704 | 26,275 | +92% | 1 | 1 | 0% | 2,078 | 2,523 | +21% | 0 | 0 | — |
case-08 | fail→fail | 14,798 | 10,913 | -26% | 1 | 1 | 0% | 2,374 | 2,316 | -2% | 0 | 0 | — |
case-09 | pass→pass | 23,043 | 20,124 | -13% | 1 | 1 | 0% | 3,398 | 3,706 | +9% | 0 | 0 | — |
case-10 | pass→pass | 16,704 | 24,796 | +48% | 1 | 1 | 0% | 2,624 | 3,044 | +16% | 0 | 0 | — |
case-11 | pass→pass | 14,460 | 11,853 | -18% | 1 | 1 | 0% | 2,054 | 2,292 | +12% | 0 | 0 | — |
case-12 | pass→pass | 15,487 | 14,122 | -9% | 1 | 1 | 0% | 2,394 | 2,913 | +22% | 0 | 0 | — |
case-13 | pass→pass | 18,609 | 19,737 | +6% | 1 | 1 | 0% | 3,072 | 3,587 | +17% | 0 | 0 | — |
case-14 | pass→pass | 15,734 | 11,166 | -29% | 1 | 1 | 0% | 2,196 | 2,359 | +7% | 0 | 0 | — |
case-15 | fail→pass | 24,269 | 18,799 | -23% | 1 | 1 | 0% | 3,193 | 3,544 | +11% | 0 | 0 | — |
case-16 | pass→pass | 13,421 | 14,064 | +5% | 1 | 1 | 0% | 1,875 | 2,762 | +47% | 0 | 0 | — |
case-17 | fail→pass | 16,242 | 9,496 | -42% | 1 | 1 | 0% | 2,382 | 2,148 | -10% | 0 | 0 | — |
case-18 | fail→pass | 15,980 | 13,260 | -17% | 1 | 1 | 0% | 2,680 | 2,619 | -2% | 0 | 0 | — |
case-19 | fail→pass | 13,773 | 22,069 | +60% | 1 | 1 | 0% | 2,038 | 2,546 | +25% | 0 | 0 | — |
case-21 | pass→pass | 18,882 | 21,117 | +12% | 1 | 1 | 0% | 3,365 | 3,991 | +19% | 0 | 0 | — |
case-22 | pass→pass | 18,082 | 18,165 | +0% | 1 | 1 | 0% | 3,190 | 3,814 | +20% | 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 +32 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.