Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →スタンレー・ドラッケンミラーの投資哲学と戦略に基づいた投資アドバイスを提供。30年間無敗、年率30%近いリターンを達成した伝説的投資家の思考法を活用し、マクロ経済分析、リスク管理、ポジション構築、市場サイクルの読み方などについて実践的な指導を行う。投資判断、市場分析、リスク管理、ポートフォリオ構築などの相談時に使用。
.claude/skills/nicepkg-stanley-druckenmiller-investment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 29% | 0% |
スタンレー・ドラッケンミラーの投資哲学と30年にわたる実績に基づいて、投資に関する実践的なアドバイスを提供します。
このスキルは、以下のようなドラッケンミラーの核心的な投資原則に基づいてアドバイスを行います：
ユーザーからの質問に対して、ドラッケンミラーの思考法を適用して回答します：
詳細な分析や具体的な手法については、以下のリファレンスファイルを参照します：
references/investment-philosophy.md を参照references/market-analysis-guide.md を参照references/case-studies.md を参照| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,991 | 25,566 | +16% | 1 | 1 | 0% | 3,031 | 3,795 | +25% | 0 | 0 | — |
case-02 | fail→fail | 23,004 | 17,522 | -24% | 1 | 1 | 0% | 3,151 | 3,366 | +7% | 0 | 0 | — |
case-03 | pass→pass | 16,782 | 13,562 | -19% | 1 | 1 | 0% | 2,309 | 2,814 | +22% | 0 | 0 | — |
case-04 | fail→pass | 15,772 | 13,752 | -13% | 1 | 1 | 0% | 2,285 | 2,762 | +21% | 0 | 0 | — |
case-05 | fail→pass | 17,214 | 17,269 | +0% | 1 | 1 | 0% | 2,509 | 3,238 | +29% | 0 | 0 | — |
case-06 | fail→pass | 15,426 | 11,720 | -24% | 1 | 1 | 0% | 2,195 | 2,393 | +9% | 0 | 0 | — |
case-07 | pass→pass | 15,804 | 13,742 | -13% | 1 | 1 | 0% | 2,215 | 2,577 | +16% | 0 | 0 | — |
case-08 | fail→pass | 14,967 | 14,422 | -4% | 1 | 1 | 0% | 2,128 | 2,752 | +29% | 0 | 0 | — |
case-09 | pass→pass | 17,531 | 15,095 | -14% | 1 | 1 | 0% | 2,227 | 2,751 | +24% | 0 | 0 | — |
case-10 | fail→pass | 17,496 | 16,897 | -3% | 1 | 1 | 0% | 2,511 | 3,209 | +28% | 0 | 0 | — |
case-11 | pass→pass | 17,539 | 16,326 | -7% | 1 | 1 | 0% | 2,577 | 3,238 | +26% | 0 | 0 | — |
case-12 | pass→pass | 16,690 | 15,841 | -5% | 1 | 1 | 0% | 2,326 | 3,140 | +35% | 0 | 0 | — |
case-13 | pass→pass | 14,002 | 13,875 | -1% | 1 | 1 | 0% | 2,244 | 2,887 | +29% | 0 | 0 | — |
case-14 | fail→fail | 12,660 | 11,662 | -8% | 1 | 1 | 0% | 1,911 | 2,681 | +40% | 0 | 0 | — |
case-15 | pass→pass | 14,208 | 14,963 | +5% | 1 | 1 | 0% | 2,067 | 2,778 | +34% | 0 | 0 | — |
case-16 | fail→pass | 18,120 | 18,812 | +4% | 1 | 1 | 0% | 2,737 | 3,510 | +28% | 0 | 0 | — |
case-17 | pass→pass | 13,237 | 13,455 | +2% | 1 | 1 | 0% | 1,955 | 2,764 | +41% | 0 | 0 | — |
case-18 | pass→pass | 14,417 | 14,785 | +3% | 1 | 1 | 0% | 2,091 | 2,993 | +43% | 0 | 0 | — |
case-19 | pass→pass | 18,146 | 19,815 | +9% | 1 | 1 | 0% | 2,502 | 3,436 | +37% | 0 | 0 | — |
case-20 | fail→fail | 32,003 | 26,204 | -18% | 1 | 1 | 0% | 6,201 | 5,607 | -10% | 0 | 0 | — |
case-21 | fail→fail | 23,326 | 23,059 | -1% | 1 | 1 | 0% | 3,859 | 4,496 | +17% | 0 | 0 | — |
case-22 | fail→fail | 15,328 | 15,106 | -1% | 1 | 1 | 0% | 3,081 | 3,550 | +15% | 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.
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.