image-to-editable-ppt-skill
ningzimu/image-to-editable-ppt-skill
An advanced AI skill that converts images, PDFs, and image-based presentations into fully editable PowerPoint (.pptx) decks. It utilizes a multi-agent reconstruction and verification loop to separate text, simple shapes, and visual components.
2k 115MITUpdated 2026-07-28
75
GreatOverview
This skill acts as a specialized pipeline to turn static slide images or PDFs into native, editable PowerPoint files. By splitting tasks across page workers, it performs OCR text extraction, coordinate layout mapping, shape vectorization, and multi-round visual QA to ensure the reconstructed slide closely matches the original source.
Capabilities
- ▸Multi-page and single-page document ingestion (images, PDFs, image-based PPT)
- ▸Native text box and font size recovery using OCR integration (PaddleOCR-VL)
- ▸Simple geometric shape detection and vectorization
- ▸Complex visual element cropping and independent asset management
- ▸Multi-agent parallel page processing with self-correction and iterative QA loops
Best for
Converting legacy PDF presentations or image-based slides into fully editable .pptx files, Revamping screenshots of charts, infographics, or reports into adjustable PowerPoint objects, Isolating text, geometric shapes, and image assets from static graphic slides for redesign
Works with
Codex
Evoa Score breakdown= Σ (score × weight)
75Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%42 → +5.0
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%50 → +7.5
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%84 → +6.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total75.1 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Executes local CLI commands, interacts with external OCR and image generation APIs, and requires broad file read/write permissions.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.