What does this skill do, and when should you use it?
This skill is the built-in pdf skill of the Open Cowork repository, an MIT-licensed open-source AI agent desktop app, located at .claude/skills/pdf/SKILL.md. It is a structured guide that teaches an AI agent to handle PDFs using Python libraries (pypdf, pdfplumber, reportlab) and command-line tools (pdftotext, qpdf, pdftk), covering text/table extraction, PDF creation, merging/splitting, rotation, watermarks, encryption, and OCR of scanned documents. Form filling is delegated to a separate FORMS.md, and advanced features plus JavaScript libraries (pdf-lib, pypdfium2) live in REFERENCE.md. Note that the skill itself declares a proprietary license (complete terms in LICENSE.txt), which differs from the repository's overall MIT license.
- Merges, splits, and rotates pages, reads metadata, applies watermarks, and sets password encryption with pypdf
- Extracts layout-aware text with pdfplumber and exports tables to pandas DataFrames or Excel
- Creates styled multi-page PDFs from scratch via reportlab (Canvas or Platypus)
- Runs CLI tools like pdftotext, qpdf, and pdftk for merging, splitting, rotation, and decryption
- OCRs scanned PDFs by converting pages to images and running pytesseract
- Follows FORMS.md for form filling (pdf-lib or pypdf)
- An office worker who needs to merge multiple PDFs into one deliverable
- A data analyst extracting tables from report PDFs and exporting them to Excel
- A developer generating PDF reports with titles and body content programmatically
- A user with a password-protected PDF who needs to decrypt it with a known password
- Anyone needing OCR text extraction from a scanned PDF
- A team batch-applying watermarks or encryption for document distribution
- Not suited for visually editing PDF page content — this skill only does programmatic processing
- If you prefer a Node.js-first workflow, pdf-lib is only referenced in REFERENCE.md; the core SKILL.md is Python-centric
- The skill declares a proprietary license; verify LICENSE.txt if your project requires strict MIT compatibility
How do you install this skill?
- Shell / CLI
- Local filesystem
Python 3 with pypdf, pdfplumber, reportlab, pytesseract, pdf2imagepoppler-utils (pdftotext, pdfimages)qpdfpdftk (optional)
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/OpenCoworkAI/open-cowork.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.claude/skills/pdf" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Merge doc1.pdf, doc2.pdf, and doc3.pdf in this folder into a single merged.pdf
- Extract all tables from report.pdf and export them to an Excel file extracted_tables.xlsx
- Apply the watermark from watermark.pdf to every page of contract.pdf
- This scanned.pdf is a scan — OCR it and extract all the text
The skill ships inside the Open Cowork desktop app under .claude/skills/pdf/ and is triggered automatically when a user request involves PDF processing; the SKILL.md itself is the guide, and the agent picks the appropriate Python library or CLI tool from its code examples. Form filling requires reading FORMS.md; advanced usage is in REFERENCE.md. Core dependencies must be available in the environment: bash
pip install pypdf pdfplumber reportlab pytesseract pdf2image
What are this skill's strengths and limitations?
- Covers the full PDF task surface: extraction, creation, merge/split, watermark, encryption, OCR, forms
- Provides both Python and command-line paths for the same tasks, letting the agent match the environment
- Includes a quick-reference table mapping tasks to the best tool
- Ships runnable example code for scanned PDFs and Excel table export
- Effectiveness depends on Python libraries, poppler-utils, qpdf, and tesseract being installed in the environment
- Form filling and advanced features are outside the SKILL.md body, requiring FORMS.md / REFERENCE.md
- pdftk is marked 'if available' and is not present in every environment
- The skill declares a proprietary license; its relationship to the repo's MIT license must be checked in LICENSE.txt
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Open Cowork PDF Skill this page | 69 · Recommended | ★ 2.2k | 12d ago | MIT |
| DeepTutor PDF Skill | 61 · Recommended | ★ 41k | 17d ago | Apache-2.0 |
| PDF Document Workflow ✓ OpenAI · Official | 46 · Use with care | ★ 28k | 4mo ago | — |
| PDF Document Processing Skill ✓ Anthropic · Official | 45 · Not recommended | ★ 181k | 16d ago | — |
| Legal Analysis PDF Report Generator | 47 · Use with care | ★ 1.8k | 7mo ago | — |
The repository README compares Open Cowork against Claude Cowork and OpenClaw, but those are app-level comparisons; for the PDF skill itself, the realistic alternative is hand-writing pypdf/pdfplumber scripts — this skill's value is pre-organized tool selection and example code the agent can follow directly.
How did FollowSkills review this skill?
Also a bundled copy of Anthropic's official pdf skill (this site has separately written a detailed profile for the official anthropics/skills source) — content is trustworthy but the version may lag.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
This review was completed under FSRS 1.0. Dimension scores are not converted; it is queued for re-review under FSRS 2.0.
See the full review method →