PDF Batch Processing Tool

Batch process PDF files - merge multiple PDFs, split PDF into multiple files, rotate pages, extract text, extract images, compress PDFs. Use when you need to...

Security Scan

The skill mostly matches its stated purpose (local PDF processing) and contains benign-looking scripts, but the README claims features (image extraction, compression) that are not present in the included files — an incoherence users should understand before installing.

Purpose & Capability

SKILL.md advertises merge, split, rotate, extract text, extract images, and compress PDF. The package includes scripts for merge, split, rotate, and extract_text, but there are no scripts for 'extract images' or 'compress PDFs' despite requirements.txt including Pillow (which would support image work). This mismatch between claimed capabilities and provided artifacts is a notable inconsistency.

Instruction Scope

Runtime instructions tell the agent to run local Python scripts on user-provided file paths; the scripts operate on files/directories provided as arguments and do not access network endpoints, environment variables, or unrelated system paths. No evidence of data exfiltration in the instructions or code.

Install Mechanism

There is no install spec beyond a plain pip suggestion (pip install pypdf pillow) in SKILL.md and a simple requirements.txt listing pypdf and Pillow — both are well-known packages. No downloads from arbitrary URLs or archive extraction.

Credentials

The skill requests no environment variables, no credentials, and references no config paths. The level of access requested is appropriate for a local file-processing utility.

Persistence & Privilege

The skill does not request 'always: true' or other elevated persistence. It is user-invocable and allowed to be invoked autonomously by the agent (the platform default), which is normal; the skill does not modify other skills or system-wide settings.

What to consider before installing

This skill appears to be a local PDF utility and the included scripts are benign and file-local, but the SKILL.md overclaims features: it advertises image extraction and PDF compression that are not implemented in the included files. Before installing or using it: 1) don't assume missing features exist — ask the publisher or inspect for scripts like extract_images.py and compress_pdf.py; 2) if you need image extraction/compression, either implement or obtain verified code, or run this in a sandbox and test on non-sensitive PDFs; 3) pip dependencies (pypdf, Pillow) are standard — review versions you install; 4) if you want to avoid any autonomous invocation, disable the skill or only invoke it manually. If the mismatch (advertised vs provided) is unexpected, treat this as a sign the package may be incomplete or poorly maintained rather than malicious, but verify before using on important data.

PDF Batch Processor

Batch process multiple PDF files with common operations. No need for expensive online services - process locally, keep your data private.

Core Capabilities

1. Merge multiple PDFs

• Combine multiple PDF files into one
• Preserve page order
• Add table of contents optional

2. Split a PDF

• Split by page ranges
• Split each page into a separate file
• Extract specific pages

3. Rotate pages

• Rotate all pages or specific page ranges
• Support 90/180/270 degree rotation

4. Extract text

• Extract text from all pages
• Export to plain text or markdown
• Batch extract from multiple PDFs in a folder

5. Extract images

• Save all images from a PDF to separate image files
• Preserve original image quality when possible

6. Compress PDF

• Reduce file size for web/email
• Three compression levels (low/medium/high)

Usage Examples

Merge multiple PDFs

python scripts/merge_pdfs.py --output combined.pdf file1.pdf file2.pdf file3.pdf

Split PDF into individual pages

python scripts/split_pdfs.py --input document.pdf --output output-folder/ --mode pages

Extract all text from PDFs in a folder

python scripts/extract_text.py --input ./pdfs/ --output ./text/

Rotate all pages 90 degrees clockwise

python scripts/rotate_pdf.py --input input.pdf --output output.pdf --degrees 90

Installation

pip install pypdf pillow

When to use this skill

✅ Use when:

• You have multiple PDFs that need the same operation
• You want to keep processing local (private, no uploads needed)
• You need to automate PDF processing in a workflow

❌ Don't use when:

• You only need to edit one page manually (use a GUI PDF editor)
• The PDF is encrypted/scanned image-only (needs OCR first)
• You need advanced editing (add/remove content, edit text)

Notes

• Works with standard PDF files
• For scanned/image PDFs you need OCR first (use an OCR tool before processing)
• All processing is local - your files never leave your machine