How do I install the PDF skill?

Run npx skillmds@latest add team-commonly/pdf in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with PDF?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

team-commonly (@team-commonly) published this skill. Their other Agent Skills are listed on their SkillMD profile.

PDF by team-commonly — Agent Skill

Name: PDF
Author: team-commonly

PDF

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).

File contents

pdf — PDF manipulation toolkit

The gateway image ships:

pdftotext, pdftoppm, pdfinfo from poppler-utils (apt)
pypdf (Python) for programmatic merge / split / metadata edits

Common operations

Extract text from a PDF

pdftotext /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.

Count pages

pdfinfo /workspace/$(basename "$PWD")/input.pdf | grep Pages

Render a page to PNG (preview / OCR input)

# 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

Merge multiple PDFs

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

Split a PDF into per-page files

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

Edit PDF metadata

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

When NOT to use this skill

To read a PDF for context — use markdown-converter (cleaner output).
To create a PDF from markdown — use pandic-office (pandoc).
To create or edit Office docs (DOCX/XLSX/PPTX) — use officecli.

---name: pdfdescription: 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).---# pdf — PDF manipulation toolkitThe gateway image ships:- `pdftotext`, `pdftoppm`, `pdfinfo` from `poppler-utils` (apt)- `pypdf` (Python) for programmatic merge / split / metadata edits## Common operations### Extract text from a PDF```bashpdftotext /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 usesmarkitdown and handles tables better). Use `pdftotext` only when you needraw text quickly.### Count pages```bashpdfinfo /workspace/$(basename "$PWD")/input.pdf | grep Pages```### Render a page to PNG (preview / OCR input)```bash# All pages → PNG at 150dpipdftoppm -png -r 150 /workspace/$(basename "$PWD")/input.pdf /workspace/$(basename "$PWD")/page# Just page 1pdftoppm -png -r 150 -f 1 -l 1 /workspace/$(basename "$PWD")/input.pdf /workspace/$(basename "$PWD")/cover```### Merge multiple PDFs```pythonpython3 - <<'PY'from pypdf import PdfWriterw = PdfWriter()for f in ["a.pdf", "b.pdf", "c.pdf"]: w.append(f)w.write("/workspace/$(basename "$PWD")/merged.pdf")PY```### Split a PDF into per-page files```pythonpython3 - <<'PY'from pypdf import PdfReader, PdfWriterr = 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```### Edit PDF metadata```pythonpython3 - <<'PY'from pypdf import PdfReader, PdfWriterr = 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```## When NOT to use this skill- To *read* a PDF for context — use `markdown-converter` (cleaner output).- To *create* a PDF from markdown — use `pandic-office` (pandoc).- To create or edit Office docs (DOCX/XLSX/PPTX) — use `officecli`.

Frequently asked questions

PDF