# ningzimu/image-to-editable-ppt-skill

Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.

Repository: https://github.com/ningzimu/image-to-editable-ppt-skill
Canonical: https://ross.abutalabs.com/products/image-to-editable-ppt-skill
Homepage: https://ppt-skill.ningzimu.vip
Language: Python
License: MIT
License Family: permissive
Topics: codex, codex-skill, editable-ppt, image-to-ppt, imagegen, multi-agent, pdf-to-pptx, powerpoint, pptx, presentation
Last push: 2026-07-28T07:00:30+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 93, longevity 7
- inputs: {"age_days": 104, "days_push": 36, "days_rel": 45, "gap_med": 11.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2180, forks 129 (observed 2026-08-28T04:06:23.007014+00:00)

## What it is
A Codex skill that converts slide images, PDFs, and image-based PPTX files into fully editable PowerPoint decks. It normalizes inputs into per-page tasks, then reconstructs text as native text boxes, simple geometry as PowerPoint shapes, and complex visuals as separate image assets using OCR and image generation/editing in a multi-agent rebuild-and-verify loop.

## Use cases
- convert screenshots of slides into an editable pptx
- turn a pdf deck into editable powerpoint slides
- rebuild image-based pptx files with native text boxes and shapes
- recover text and shapes from slide images for editing
- extract editable elements from scanned presentations
- make a picture-only presentation editable again

## When to choose
- you have image-based or scanned slides that must become editable PowerPoint files
- you need text, shapes, and visual assets separated for object-level editing
- you use Codex with full access and can tolerate long, token-heavy multi-agent runs

## When to avoid
- you just want to generate a new presentation from an outline or article (use a generation skill instead)
- you need a fast, lightweight conversion or have limited API/token budget
- you cannot grant full-access permissions or approve frequent tool calls during long runs

## Facets
- artifact type: plugin
- maturity: active
- function: ocr, image-processing, pdf, agent-framework, llm-inference, developer-tools
- domain: developer-tools, artificial-intelligence, pdf, files
- platform: python, cli, cross-platform
- tags: codex-skill, pptx, powerpoint, image-to-ppt, pdf-to-pptx, editable-slides, multi-agent, slide-reconstruction, paddleocr, automation

## Member repositories
- ningzimu/image-to-editable-ppt-skill (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:23.007014+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:48:43.912509+00:00, confidence not recorded.
  - readme: https://github.com/ningzimu/image-to-editable-ppt-skill (fetched 2026-08-28T04:06:23.007014+00:00, sha 482a6fdacd7c)
  - homepage: https://ppt-skill.ningzimu.vip (fetched 2026-08-29T10:28:36.845131+00:00, sha 125e5d34f405)
- Data as of 2026-08-30T08:39:29.467469+00:00.