From openai-office-skills
Handles PDF reading, creation, and review with visual rendering (Poppler/pdftoppm) and Python tools (reportlab for generation, pdfplumber/pypdf for extraction).
npx claudepluginhub fcakyon/claude-codex-settings --plugin openai-office-skillsThis skill uses the workspace's default tool permissions.
- Read or review PDF content where layout and visuals matter.
Reads, creates, and reviews PDFs with layout fidelity: renders pages via Poppler for visual checks, generates with reportlab, extracts text using pdfplumber or pypdf.
Reads, creates, and reviews PDFs with visual rendering checks via Poppler/pdftoppm to PNGs, using reportlab for generation and pdfplumber/pypdf for extraction where layout matters.
Reads, extracts content from, generates, and visually validates PDFs using reportlab, pdfplumber, and PNG rendering with pdftoppm. For layout-sensitive PDF tasks.
Share bugs, ideas, or general feedback.
pdftoppm if available.reportlab to generate PDFs when creating new documents.pdfplumber (or pypdf) for text extraction and quick checks; do not rely on it for layout fidelity.tmp/pdfs/ for intermediate files; delete when done.output/pdf/ when working in this repo.Prefer uv for dependency management.
Python packages:
uv pip install reportlab pdfplumber pypdf
If uv is unavailable:
python3 -m pip install reportlab pdfplumber pypdf
System tools (for rendering):
# macOS (Homebrew)
brew install poppler
# Ubuntu/Debian
sudo apt-get install -y poppler-utils
If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.
No required environment variables.
pdftoppm -png $INPUT_PDF $OUTPUT_PREFIX