Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assists users in crafting high-impact pitches, presentations, and sales communications using the "STRONG" method and Frame Control. Use when users want to pitch an idea to investors, sell a product to a client, or need to overcome objections and command attention in business meetings.
.claude/skills/kuhung-persuasion-pitch/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 32% | 0% |
This skill provides procedural guidance for crafting and delivering high-stakes pitches and handling business communications based on the principles of Neuroeconomics and Frame Control (from the book Pitch Anything by Oren Klaff).
Your primary goal is to bypass the analytical "Neocortex" and appeal directly to the "Crocodile Brain" (the primal part of the brain that makes initial decisions based on survival and novelty).
The Crocodile Brain's Rules:
Strategic Nuances (The Edge):
Your Communication Style:
When a user asks you to help structure a pitch, use the STRONG framework:
When users ask for advice on handling difficult meetings, negotiations, or objections, guide them using Frame Control.
Types of Frames You Will Encounter:
Counter-Frames (Your Arsenal):
When reviewing a user's script, email, or presentation:
For deeper arguments and source material, see notes/说服的艺术_笔记.md.
本章节沉淀该方法论在实战中被修正的经验(第二次残差),随使用持续更新。
使用方式:在任何项目中对 Agent 说"记入实战修正",以 - YYYY-MM-DD: 经验内容 格式追加至此。全局挂载为软链接,此处的修改会直接写回 book-skills 仓库工作区,记得回仓库提交。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | fail→pass | 13,604 | 12,060 | -11% | 1 | 1 | 0% | 2,116 | 2,875 | +36% | 0 | 0 | — |
case-01 | fail→fail | 22,403 | 19,305 | -14% | 1 | 1 | 0% | 3,535 | 4,070 | +15% | 0 | 0 | — |
case-02 | fail→fail | 16,995 | 14,645 | -14% | 1 | 1 | 0% | 2,485 | 3,317 | +33% | 0 | 0 | — |
case-03 | pass→pass | 16,179 | 14,614 | -10% | 1 | 1 | 0% | 2,367 | 3,316 | +40% | 0 | 0 | — |
case-04 | fail→pass | 11,743 | 9,654 | -18% | 1 | 1 | 0% | 1,837 | 2,480 | +35% | 0 | 0 | — |
case-05 | fail→pass | 9,836 | 9,855 | +0% | 1 | 1 | 0% | 1,615 | 2,561 | +59% | 0 | 0 | — |
case-06 | pass→pass | 15,583 | 10,933 | -30% | 1 | 1 | 0% | 2,181 | 2,673 | +23% | 0 | 0 | — |
case-07 | fail→pass | 11,134 | 8,508 | -24% | 1 | 1 | 0% | 1,514 | 2,259 | +49% | 0 | 0 | — |
case-08 | fail→pass | 12,184 | 9,873 | -19% | 1 | 1 | 0% | 1,843 | 2,427 | +32% | 0 | 0 | — |
case-09 | pass→pass | 10,287 | 9,311 | -9% | 1 | 1 | 0% | 1,545 | 2,361 | +53% | 0 | 0 | — |
case-10 | pass→pass | 9,130 | 9,974 | +9% | 1 | 1 | 0% | 1,528 | 2,608 | +71% | 0 | 0 | — |
case-11 | pass→pass | 14,040 | 8,847 | -37% | 1 | 1 | 0% | 1,745 | 2,326 | +33% | 0 | 0 | — |
case-12 | pass→pass | 13,165 | 10,524 | -20% | 1 | 1 | 0% | 2,072 | 2,643 | +28% | 0 | 0 | — |
case-13 | pass→pass | 13,591 | 10,343 | -24% | 1 | 1 | 0% | 2,011 | 2,481 | +23% | 0 | 0 | — |
case-14 | pass→pass | 14,137 | 13,216 | -7% | 1 | 1 | 0% | 2,082 | 2,902 | +39% | 0 | 0 | — |
case-15 | pass→pass | 14,072 | 13,160 | -6% | 1 | 1 | 0% | 2,165 | 3,063 | +41% | 0 | 0 | — |
case-17 | pass→pass | 12,082 | 7,555 | -37% | 1 | 1 | 0% | 1,810 | 2,148 | +19% | 0 | 0 | — |
case-18 | fail→pass | 15,372 | 12,848 | -16% | 1 | 1 | 0% | 2,198 | 2,771 | +26% | 0 | 0 | — |
case-19 | fail→pass | 13,316 | 14,921 | +12% | 1 | 1 | 0% | 2,208 | 3,197 | +45% | 0 | 0 | — |
case-20 | pass→fail | 3,888 | 6,937 | +78% | 1 | 1 | 0% | 877 | 2,311 | +164% | 0 | 0 | — |
case-21 | pass→fail | 14,136 | 10,382 | -27% | 1 | 1 | 0% | 2,123 | 2,717 | +28% | 0 | 0 | — |
case-22 | pass→pass | 15,060 | 10,526 | -30% | 1 | 1 | 0% | 2,632 | 2,813 | +7% | 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 +23 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.