Yuan1z0825/nature-skills / skills/nature-image2ppt
nature-image2ppt
FlaggedReconstruct slide images, screenshots, scanned PDFs, or image-only PPTX files as object-level editable PowerPoint. Use for 图片转可编辑PPT、截图还原PPT and diagram reconstruction; not authoring a new deck from research notes.
references/assets-provenance-contract.md
View on GitHub# Assets and Provenance Contract
## Separate image production from page assembly
The agent image tool or the bundled `image generate/edit` backend produces image
files. The deterministic local CLI imports, validates, records, chroma-cleans, and
splits those outputs. Never infer a generated result by scanning for the newest
file; import only the explicit returned path.
Use an image only for a clean background, a bounded style-bearing foreground
object, a complex local diagram subpart, a user-provided visual, an approved
rasterization, or a rendered formula. Do not use a full-slide screenshot as a
hidden base and do not flatten a measurable knowledge graph.
## `imagegen-jobs.json`
`prepare` creates one page-local job ledger. `image import` records the actual
producer, selected file, destination, hash, role, and fallback reason. `image
process-sheet` records chroma cleanup and split artifacts. These are asset records,
not a second page state machine.
Every recorded source, destination, split artifact, and provenance path must
resolve inside the owning page directory. An absolute path may be used as the
input to `image import` or as the explicit `process-sheet --asset-sheet-source`
only long enough to copy a selected image-tool result into the page; it must never
be recorded as the page asset path or reused as a build dependency. Relative
inputs remain page-confined and may not use `..` traversal.
Valid producer identifiers are `builtin-imagegen`, `codex-oauth`, and
`openai-compatible-api`. A fallback reason is allowed only when it matches the
run/page image-backend contract. Record the exact provider model id with
`image2ppt image import --model` when it is known; provider-specific model ids do
not create new producer identifiers because the producer boundary is the transport
backend plus the recorded model.
## `manifest.json.asset_provenance`
Every `images[].path` requires one matching provenance item with:
- `path`: the exact path referenced by the page image object;
- `source`: an existing source, asset sheet, or formula source file;
- `source_type`: `asset-sheet-separated`, `imagegen`,
`latex-rendered-formula`, `user-provided`, or
`user-approved-rasterization`;
- `provenance_note`: a non-empty production explanation;
- `approval_note`: additionally required for user-approved rasterization.
Record foreground visuals as source-faithful image-edit/asset-sheet separation.
Native structural circles, lines, cards, and connectors should be described as
native structure, not as image assets. Keep every complex asset bounded to its
actual source region and give it useful alt text.
## Security and network boundary
Online OCR and image services receive only the task-local pages, prompts, masks,
and references necessary for the requested conversion. Request required network
approval before sending sensitive material. Keep API keys and OAuth files outside
the Skill and run directories; diagnostic output must expose only set/unset status.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |