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/runtime-dependencies.md
View on GitHub# Runtime Dependencies
Image2PPT runs entirely from this Skill directory. It neither imports another Skill
nor requires another command-line package.
## Python
Use Python 3.10 or later and install the bundled requirements:
```bash
python -m pip install -r <image2ppt-root>/requirements.txt
```
Copying or synchronizing the Skill does not install Python packages. Run the
command above in the Python environment that will execute the CLI, then require a
successful `doctor --json` result before preparing an input. Prefer a dedicated
environment over modifying the operating system Python.
Required packages are pypdfium2, Pillow, NumPy, Requests, PyYAML, and OpenAI. The
OpenAI package supports the optional image-generation fallback; OCR uses Requests.
The builder writes OOXML directly and does not require `python-pptx`.
Run without installation:
```bash
python <image2ppt-root>/cli/image2ppt/cli.py --help
```
Optionally install the bundled wrapper:
```bash
python -m pip install --editable <image2ppt-root>/cli
image2ppt --help
```
## System programs
- Windows: PowerPoint automation plus PowerShell is preferred for rendered QA.
- Linux/macOS: LibreOffice/`soffice` is required for Office input conversion and
rendered QA.
- Fonts: install a usable sans font; Noto Sans CJK or Microsoft YaHei is strongly
recommended for Chinese pages.
- ImageMagick is optional for formula PNG conversion and unusual image formats;
Pillow is the primary image processor.
- Formula rendering optionally uses a TeX engine plus `dvisvgm`, `pdf2svg`, or
ImageMagick. Missing formula tooling is a hard failure for formula-bearing pages
unless the user explicitly approves omission of that exact formula.
Ubuntu/Debian example:
```bash
sudo apt-get install libreoffice-impress fonts-noto-cjk imagemagick
```
## Configuration
Persistent secrets live in the active `config.yaml`: the directory selected by
`IMAGE2PPT_CONFIG_HOME`, then the project-level Skill root, then the legacy
`~/.image2ppt/` location. Process environment variables take precedence. Do not
place a real token/key in a run directory, Prompt, manifest, report, or source control.
Run the independent checks:
```bash
python <image2ppt-root>/cli/image2ppt/cli.py doctor --json
```
Doctor is the sole runtime preflight. It reports Python imports, local
CLI/resources, LibreOffice/PowerPoint rendering, OCR endpoint/model/token/fallback,
image backend readiness, fonts, Pillow, and ImageMagick. It never makes an OCR
request unless a separate smoke test explicitly does so.
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 |