Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →マーケティング計画策定・プロダクトマーケティングコンテキスト作成スキル。 「マーケ計画」「ポジショニング」「ペルソナ作成」「競合分析」「コンテンツ戦略」等で発動。 product-marketing-context.mdを生成し、他のマーケティングスキルの土台を作る。
.claude/skills/minicoohei-marketing-planner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 2% | 0% |
プロダクトのマーケティング基礎文書を作成し、全マーケティング施策の土台を構築する。
marketing/product-context.md — 他スキル（content-creator, post-publisher等）が参照する共通コンテキスト。
marketing/product-context.md が存在するか確認。
以下のセクションを会話形式で埋める。一度に全部聞かない。
詳細フレームワーク → references/context-template.md
収集した情報から marketing/product-context.md を生成。
コンテキストに基づいて最適チャネルミックスを提案。 詳細 → references/channel-strategy.md
月次/週次のコンテンツ投稿計画を marketing/content-calendar.md に出力。
content-creator — コンテキストを参照してコンテンツ制作post-publisher — 制作コンテンツを各プラットフォームに投稿product-marketing-context, content-strategy, marketing-ideas, launch-strategy| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 14,037 | 2,931 | -79% | 1 | 1 | 0% | 2,505 | 819 | -67% | 0 | 0 | — |
case-01 | fail→fail | 8,964 | 3,552 | -60% | 1 | 1 | 0% | 1,392 | 1,045 | -25% | 0 | 0 | — |
case-02 | fail→fail | 18,232 | 4,350 | -76% | 1 | 1 | 0% | 2,739 | 1,079 | -61% | 0 | 0 | — |
case-03 | fail→pass | 7,971 | 4,448 | -44% | 1 | 1 | 0% | 1,282 | 1,105 | -14% | 0 | 0 | — |
case-04 | pass→pass | 13,970 | 11,293 | -19% | 1 | 1 | 0% | 2,481 | 2,525 | +2% | 0 | 0 | — |
case-05 | pass→pass | 14,658 | 8,381 | -43% | 1 | 1 | 0% | 2,484 | 1,830 | -26% | 0 | 0 | — |
case-06 | pass→pass | 13,523 | 11,394 | -16% | 1 | 1 | 0% | 2,169 | 1,974 | -9% | 0 | 0 | — |
case-07 | pass→pass | 12,686 | 2,975 | -77% | 1 | 1 | 0% | 2,092 | 868 | -59% | 0 | 0 | — |
case-08 | pass→pass | 11,046 | 5,525 | -50% | 1 | 1 | 0% | 1,753 | 1,263 | -28% | 0 | 0 | — |
case-09 | fail→pass | 13,241 | 9,892 | -25% | 1 | 1 | 0% | 1,983 | 1,954 | -1% | 0 | 0 | — |
case-10 | fail→pass | 24,376 | 3,208 | -87% | 1 | 1 | 0% | 1,928 | 830 | -57% | 0 | 0 | — |
case-12 | pass→pass | 18,168 | 11,441 | -37% | 1 | 1 | 0% | 2,767 | 2,065 | -25% | 0 | 0 | — |
case-13 | pass→pass | 16,272 | 11,468 | -30% | 1 | 1 | 0% | 2,502 | 2,106 | -16% | 0 | 0 | — |
case-14 | pass→pass | 15,693 | 8,567 | -45% | 1 | 1 | 0% | 2,355 | 1,721 | -27% | 0 | 0 | — |
case-15 | pass→pass | 14,698 | 10,375 | -29% | 1 | 1 | 0% | 2,288 | 1,882 | -18% | 0 | 0 | — |
case-16 | pass→pass | 16,100 | 13,027 | -19% | 1 | 1 | 0% | 2,538 | 2,239 | -12% | 0 | 0 | — |
case-17 | fail→fail | 15,568 | 4,880 | -69% | 1 | 1 | 0% | 2,368 | 1,258 | -47% | 0 | 0 | — |
case-18 | fail→fail | 12,299 | 4,350 | -65% | 1 | 1 | 0% | 1,827 | 1,175 | -36% | 0 | 0 | — |
case-19 | pass→pass | 15,047 | 6,197 | -59% | 1 | 1 | 0% | 2,510 | 1,344 | -46% | 0 | 0 | — |
case-20 | pass→pass | 14,006 | 7,831 | -44% | 1 | 1 | 0% | 2,239 | 1,655 | -26% | 0 | 0 | — |
case-21 | fail→fail | 7,328 | 8,080 | +10% | 1 | 1 | 0% | 1,091 | 1,417 | +30% | 0 | 0 | — |
case-22 | pass→pass | 9,337 | 1,807 | -81% | 1 | 1 | 0% | 1,564 | 625 | -60% | 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 +18 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.