Image To Editable PptSAFE

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

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: image-to-editable-ppt
description: Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied. Use for making visual slides editable or reconstructing slides from screenshots; not for authoring new presentations from scratch.
---
# Image to Editable PPT

## Overview

Use the `editppt` runtime to decompose, reconstruct, validate, and assemble visual slides as editable `.pptx`. Inputs may be single or multiple images, PDF, or image-based PPT/PPTX.

## References

Each rule in this skill has exactly one authoritative home; the other files point to it instead of restating it.

- `prompts/page-worker.md`: execution template for page workers — ownership boundary, execution order, required outputs, and return format. The parent agent uses it when generating page-worker prompts.
- `scripts/build-page-worker-prompt.py`: skill-local prompt builder. It reads `prompts/page-worker.md`, fills run/page paths, writes `worker-prompt.md`, and prints the dispatch command template.
- `references/cli-helper.md`: CLI install check (Pre-Run Check), command tree, and command syntax examples. Read it when deciding which `editppt` command to call.
- `references/manifest-schema.md`: the single home for JSON field contracts of deck/page/image artifacts — required manifest fields, positioned-object coordinates, `validation.json`, and `page_result.json` shapes. Read it when writing or validating any run/page file.
- `references/page-decision-tree.md`: the single source of truth for page object decisions — background handling, foreground asset separation, native shapes, formulas, text-hints usage, the final self-check, and the fix-versus-warning split. Read its common decision boundaries first, then the sections relevant to the page inventory; the page prompt provides the reading route.

## Entry Contract

These parent-level rules are stated once here; page-level rules live in the references above and are not restated in this file.

- The `editppt` CLI is a required runtime surface. If `editppt --help` fails, install it first by following the Pre-Run Check in `references/cli-helper.md` before doing anything else.
- First run `editppt prepare <input...>` to create a run directory. After that, all key state transitions are advanced only through `editppt` commands; never hand-write run/page state JSON. This keeps run state deterministic and resumable.
- Multi-page inputs are rebuilt by dispatched page workers. A run with exactly one page is rebuilt by the parent agent in local page-reconstructor mode after `editppt run dispatch --local` claims that page. If no subagent capability is available for a multi-page run, stop and report this to the user; do not degrade into parent-agent reconstruction for multi-page input.
- The parent agent must not write any page reconstruction artifact — `manifest.json`, `page.pptx`, `preview.png`, `split_assets_contact.png`, `validation.json`, or `page_result.json` — except in single-page local page-reconstructor mode after `editppt run dispatch --local` has recorded the claim. Local mode follows the same page prompt, references, output files, and `run record` validation path as a page worker.
- All image generation, image editing, background repair, transparent bitmap assets, and asset sheets follow the serial per-page backend order in "Image Backend Selection" below.
- A user request to convert visual slides into editable PPT authorizes the required OCR and image-backend calls for that conversion, unless the user explicitly requests local-only processing or marks the input as confidential/no-external-processing. Do not refuse solely because the workflow calls PaddleOCR, the built-in `image_gen.imagegen` tool, Codex OAuth/ChatGPT image endpoints, or a user-configured OpenAI-compatible API; those calls are necessary to the skill.
- Only send task-local page images, prompts, masks, and reference images required for the current conversion. Never send unrelated local files, API keys, auth tokens, credentials, or generated artifacts that are not needed by the current OCR/image operation. Third-party API endpoints are allowed only when already configured by the user or explicitly specified for this run.
- In network-restricted environments, request any approval required by the current runtime before external OCR/image calls, including `editppt prepare` or `editppt run hints` when `PADDLE_OCR_TOKEN` is set and every CLI fallback `editppt image generate/edit` call. The approval justification must say this is a user-requested `image-to-editable-ppt` conversion, that the upload is limited to task-local page images/prompts/masks/references, and that OCR/image-backend calls are part of this skill's required workflow. Do not present the required call as unsafe or ask the user to re-approve it unless they requested local-only/confidential handling or the approval system explicitly rejects the request.
- Execute routine reconstruction, configured backend fallback, and local repairs autonomously. Do not add confirmation gates; retain the OCR choices in Phase 1 and any approval required by the runtime. A missing prerequisite that only the user can supply is a concrete blocker, not a request to debug the workflow.
- All page object decisions follow `references/page-decision-tree.md`, including its no-fallback rule for foreground visual objects and its rule that deterministic validation is a structure gate that never waives an object-source decision.
- `manifest.json` is the authoritative page build source: `editppt run record` validates `page.pptx` against it, and `editppt run finalize` rebuilds the final deck from recorded page manifests. Required fields and coordinate contracts are defined in `references/manifest-schema.md`.
- `editppt prepare` writes per-page text measurements (`text_hints.json`/`text_hints.png`). How page reconstructors consume them is defined in `references/page-decision-tree

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

declared (1 observation(s))

Network

declared (4 observation(s))

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

out_path.write_bytes(base64.b64decode(image_b64))

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Image To Editable Ppt](https://modelsatlas.com/skills/ningzimu/image-to-editable-ppt/badge.svg)](https://modelsatlas.com/skills/ningzimu/image-to-editable-ppt/)

Not your listing, or something out of date? Claim or update your listing.