// Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit `markdown-converter` (general read) or `pandic-office` (write from markdown).
| name | |
| description | Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit `markdown-converter` (general read) or `pandic-office` (write from markdown). |
The gateway image ships:
pdftotext, pdftoppm, pdfinfo from poppler-utils (apt)pypdf (Python) for programmatic merge / split / metadata editspdftotext /workspace/$(basename "$PWD")/input.pdf /workspace/$(basename "$PWD")/input.txt
# Or stream to stdout:
pdftotext /workspace/$(basename "$PWD")/input.pdf -
For LLM-friendly output, prefer the markdown-converter skill (which uses
markitdown and handles tables better). Use pdftotext only when you need
raw text quickly.
pdfinfo /workspace/$(basename "$PWD")/input.pdf | grep Pages
# All pages → PNG at 150dpi
pdftoppm -png -r 150 /workspace/$(basename "$PWD")/input.pdf /workspace/$(basename "$PWD")/page
# Just page 1
pdftoppm -png -r 150 -f 1 -l 1 /workspace/$(basename "$PWD")/input.pdf /workspace/$(basename "$PWD")/cover
python3 - <<'PY'
from pypdf import PdfWriter
w = PdfWriter()
for f in ["a.pdf", "b.pdf", "c.pdf"]:
w.append(f)
w.write("/workspace/$(basename "$PWD")/merged.pdf")
PY
python3 - <<'PY'
from pypdf import PdfReader, PdfWriter
r = PdfReader("/workspace/$(basename "$PWD")/input.pdf")
for i, page in enumerate(r.pages):
w = PdfWriter()
w.add_page(page)
w.write(f"/workspace/$(basename "$PWD")/page_{i+1}.pdf")
PY
python3 - <<'PY'
from pypdf import PdfReader, PdfWriter
r = PdfReader("/workspace/$(basename "$PWD")/input.pdf")
w = PdfWriter(clone_from=r)
w.add_metadata({"/Title": "New Title", "/Author": "Theo"})
w.write("/workspace/$(basename "$PWD")/output.pdf")
PY
markdown-converter (cleaner output).pandic-office (pandoc).officecli.Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final deliverable'. Routes to `officecli merge` with one of three pre-built starter templates that already carry the Commonly palette, fonts, and structure — so you populate content with one merge call instead of 30 individual `officecli set` commands. DO NOT use for fundraising decks (use `officecli-pitch-deck`), academic papers (use `officecli-academic-paper`), or financial models (use `officecli-financial-model`).
Interact with GitHub (issues, PRs, repos, releases) using the `gh` CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's `markitdown` Python tool. Use when a user attaches a binary file and you need to read its contents.
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the `pandoc` CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).