image-to-editable-ppt

Image to Editable PPT

Overview

This skill rebuilds visual slide inputs into object-level editable PowerPoint .pptx files.

Inputs can be a single image, multiple images, a PDF, or an image-based PPT/PPTX. The output is always .pptx. The goal is not to wrap a full-slide screenshot inside PowerPoint; the goal is to use the editppt runtime and page-level prompts to decompose, reconstruct, validate, and assemble editable slides.

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 it before reconstructing any page.

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.
• 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.md section 3.1.
• Page reconstructors — either page workers or the parent agent in single-page local mode — are driven by prompts generated from prompts/page-worker.md.