Individual skill
image-ppt-king
Convert slide/page images into editable PowerPoint PPTX decks by using Image Split visual layers, region schemas, transparent editable text, and QA gates. Use when Codex is given PNG/JPG/Image2/AI-generated slide images and asked to reconstruct image-based PPT pages, keep text editable, preserve layout, or turn flat slide screenshots into PPTX with selectable text and movable image objects.
skills/image-ppt-king/SKILL.md
Source commit c319f48ee9f25fee4a7a413476e1c97c34c29acd
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 34
- Repository last updated
- May 25, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- automation Repository topic
- computer-vision Repository topic
- image-to-ppt Repository topic
- ocr Repository topic
- powerpoint Repository topic
- pptx Repository topic
- presentation Repository topic
- slides Repository topic
- design Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesSKILL.mdcore · 14,191 bytesagents/openai.yamlasset · 292 bytesassets/demo/elements.jsonasset · 1,534 bytesassets/demo/source.pngasset · 20,028 bytesassets/demo/text-layer.jsonasset · 2,052 bytesassets/demo/visual-layers/slide-01/01_header_rule.pngasset · 599 bytesassets/demo/visual-layers/slide-01/02_left_card_outline.pngasset · 4,397 bytesassets/demo/visual-layers/slide-01/03_right_card_outline.pngasset · 4,229 bytesassets/demo/visual-layers/slide-01/04_center_arrow.pngasset · 685 bytesassets/demo/visual-layers/slide-01/05_footer_rule.pngasset · 440 bytesassets/demo/visual-layers/slide-01/assets_contact_sheet.pngasset · 11,444 bytesassets/demo/visual-layers/slide-01/composite_no_text_preview.pngasset · 7,944 bytesassets/demo/visual-layers/slide-01/manifest.jsonasset · 2,027 bytespackage-lock.jsonasset · 6,812 bytespackage.jsonruns · 512 bytesreferences/acceptance-rubric.mddoc · 7,262 bytesreferences/copyslides-like-reconstruction.mddoc · 4,479 bytesreferences/runtime-and-platform.mddoc · 1,889 bytesreferences/text-layer-schema.mddoc · 4,436 bytesreferences/visual-anchor-text.mddoc · 3,163 bytesrequirements.txtdoc · 24 bytesscripts/build_ppt_from_layers.mjsruns · 19,373 bytesscripts/visual_text_qa.pyruns · 12,914 bytes
Read excerpt
# Image-PPT-King
## Contract
Build a PPTX where visual components are image/shape layers and semantic text is native editable PowerPoint text.
- Do not put final body text inside a flattened slide screenshot.
- Use `image-split` first when the input is only flat slide images and no clean visual layers exist.
- Preserve slide size, page order, visual rhythm, and page numbering.
- Treat charts, photos, microscopy, logos, and complex diagrams as image objects unless the user explicitly asks to redraw them.
- Rebuild main titles, labels, card text, bullets, captions, and page numbers as editable text boxes.
- Editable text boxes are text-only by default: no fill, no outline, no patch background.
- Prefer the Presentations artifact-tool when it is available because it can render previews and layout JSON. If it is not available, use the bundled `pptxgenjs` fallback backend to generate a reproducible editable PPTX.
