pdf-toolkit

Installation
SKILL.md

PDF Toolkit

Extract data from PDFs (text, tables, images, OCR), create new PDFs, and manipulate existing ones (merge, split). All operations use bundled Bun TypeScript scripts that produce structured JSON output.

When to use

  • The task explicitly involves PDF extraction, OCR, creation, merging, splitting, or conversion using the bundled scripts.
  • The user needs machine-processable output from PDF documents or wants to generate PDF artifacts.
  • The request is document-processing work on .pdf inputs or outputs, not general office-file editing.
  • The workflow should run through the toolkit’s existing Bun/TypeScript utilities.

Do NOT use when:

  • The files are primarily DOCX, XLSX, PPTX, or another non-PDF format.
  • The task requires interactive AcroForm filling, digital signing, or PDF encryption features the toolkit does not cover.
  • The request is general OCR with no PDF input or output requirement.
Related skills
Installs
14
GitHub Stars
4
First Seen
Mar 7, 2026