Install any skill in seconds. Free to start, no credit card required.
Get Started Free →PPTXテンプレート変換 & ゼロからデッキ生成。テーマ・アニメーション・SmartArtを保持してコンテンツを書き換え。 「PPTX変換」「スライド作成」「パワポ書き換え」「デッキ生成」等のリクエストで発動。
.claude/skills/minicoohei-pptx-converter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -77% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -12% | 0% |
「PPTX変換」「スライド作成」「パワポ書き換え」「デッキ生成」「PowerPoint」
PowerPointファイルのテンプレート変換とゼロからのデッキ生成ツール。
元PPTXをコピーして、全要素をGeminiで意味解析し、新トピックに合わせてコンテンツを自動書き換え。
bashpython skills/pptx-converter/scripts/pptx_converter.py convert \ source.pptx \ --topic "2026年Q1営業報告" \ -o output/slides/q1_report.pptx
保持されるもの: スライドマスター、テーマカラー、フォント定義、アニメーション、トランジション、SmartArt構造、レイアウト配置
元PPTXの全要素を抽出・意味解析し、座標-要素マッピングYAMLを生成。手動確認・編集用。
bashpython skills/pptx-converter/scripts/pptx_converter.py extract \ source.pptx \ -o mapping.yaml
手動編集したデータYAMLで要素を書き換え。
bashpython skills/pptx-converter/scripts/pptx_converter.py build \ source.pptx \ mapping.yaml \ --data data.yaml \ -o output.pptx
トピックからGeminiでアウトライン生成 → PPTX自動作成。
bashpython skills/pptx-converter/scripts/pptx_converter.py deck \ --topic "AIエージェント活用提案" \ --type proposal \ --style corporate \ -o output/slides/proposal.pptx
deck オプション:
--type: auto / presentation / proposal / report / educational / pitch--style: corporate / creative / minimal / academic--slides N: スライド枚数(0=AI決定)--audience: 対象者--outline-only: アウトラインYAMLのみ出力| タイプ | 抽出 | 書き換え | 備考 | |--------|:----:|:--------:|------| | テキスト | o | o | スタイル(フォント・色・太字等)完全保持 | | チャート | o | o | chart.replace_data() でデータのみ差し替え | | テーブル | o | o | セルスタイル保持、行列内容のみ差し替え | | 画像 | o | o | デフォルト保持、個別に差し替え指定可能 | | 図形 | o | o | 図形内テキストの差し替え | | グループ | o | o | 子要素を再帰的に処理(深さ3まで) | | SmartArt | o | 部分 | テキストノードのみXML直接操作で差し替え |
yamlsource: "source.pptx" generated_at: "2026-02-09T15:30:00" slide_width: 12192000 slide_height: 6858000 slides: - slide_number: 1 layout: "Title Slide" elements: - id: 2 name: "Title 1" type: text role: title hint: "メインタイトル。15-25文字。" position: { left: 457200, top: 274638, width: 8229600, height: 1143000 } style: { font: "Meiryo UI", size: 36, bold: true, color: "2563EB" } value: "2025年度 営業戦略" placeholder: "{{slide_1_title}}" placeholders: - key: "{{slide_1_title}}" type: text role: title current: "2025年度 営業戦略"
convert(1コマンド完結)extract → YAML編集 → builddeckGEMINI_API_KEY or GOOGLE_API_KEY: Gemini API キー(必須)GEMINI_FLASH_MODEL: テキスト処理モデル(デフォルト: gemini-2.5-flash)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 12,843 | 1,838 | -86% | 1 | 1 | 0% | 1,920 | 1,282 | -33% | 0 | 0 | — |
case-01 | fail→pass | 15,906 | 3,605 | -77% | 1 | 1 | 0% | 3,031 | 1,761 | -42% | 0 | 0 | — |
case-02 | fail→pass | 29,465 | 2,569 | -91% | 1 | 1 | 0% | 6,206 | 1,455 | -77% | 0 | 0 | — |
case-03 | fail→pass | 15,668 | 3,520 | -78% | 1 | 1 | 0% | 3,432 | 1,682 | -51% | 0 | 0 | — |
case-04 | fail→pass | 10,559 | 2,657 | -75% | 1 | 1 | 0% | 1,789 | 1,569 | -12% | 0 | 0 | — |
case-05 | fail→pass | 15,170 | 3,036 | -80% | 1 | 1 | 0% | 2,599 | 1,628 | -37% | 0 | 0 | — |
case-06 | fail→pass | 18,553 | 6,184 | -67% | 1 | 1 | 0% | 3,142 | 2,165 | -31% | 0 | 0 | — |
case-07 | fail→pass | 16,525 | 4,767 | -71% | 1 | 1 | 0% | 2,495 | 1,947 | -22% | 0 | 0 | — |
case-08 | pass→pass | 5,336 | 2,160 | -60% | 1 | 1 | 0% | 852 | 1,323 | +55% | 0 | 0 | — |
case-09 | fail→pass | 13,631 | 1,777 | -87% | 1 | 1 | 0% | 2,313 | 1,331 | -42% | 0 | 0 | — |
case-10 | fail→pass | 16,011 | 8,104 | -49% | 1 | 1 | 0% | 2,459 | 2,348 | -5% | 0 | 0 | — |
case-12 | pass→pass | 17,052 | 9,736 | -43% | 1 | 1 | 0% | 2,876 | 2,507 | -13% | 0 | 0 | — |
case-13 | fail→pass | 10,971 | 1,831 | -83% | 1 | 1 | 0% | 1,803 | 1,310 | -27% | 0 | 0 | — |
case-14 | pass→pass | 7,819 | 1,841 | -76% | 1 | 1 | 0% | 1,297 | 1,323 | +2% | 0 | 0 | — |
case-15 | pass→pass | 13,964 | 4,281 | -69% | 1 | 1 | 0% | 2,362 | 1,917 | -19% | 0 | 0 | — |
case-16 | pass→pass | 15,722 | 4,752 | -70% | 1 | 1 | 0% | 2,473 | 1,789 | -28% | 0 | 0 | — |
case-17 | fail→fail | 11,615 | 5,116 | -56% | 1 | 1 | 0% | 1,876 | 1,846 | -2% | 0 | 0 | — |
case-18 | pass→pass | 15,547 | 5,908 | -62% | 1 | 1 | 0% | 2,410 | 1,998 | -17% | 0 | 0 | — |
case-19 | pass→pass | 12,149 | 3,794 | -69% | 1 | 1 | 0% | 1,795 | 1,600 | -11% | 0 | 0 | — |
case-20 | pass→pass | 12,437 | 7,568 | -39% | 1 | 1 | 0% | 2,044 | 2,294 | +12% | 0 | 0 | — |
case-21 | pass→pass | 18,097 | 11,286 | -38% | 1 | 1 | 0% | 3,232 | 3,267 | +1% | 0 | 0 | — |
case-22 | pass→pass | 12,749 | 8,158 | -36% | 1 | 1 | 0% | 2,538 | 2,564 | +1% | 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 +50 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.