Extract text and coordinates from PDFs, then merge, split, rotate, or fill them.
npx skills add https://github.com/mykcs/myk-skills --skill pdf-mykcs
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/mykcs/myk-skills/tree/main/pdf Command: npx skills add https://github.com/mykcs/myk-skills --skill pdf-mykcs
This skill removes the tedium of working with PDFs by helping you reliably extract content, transform documents, and populate form fields with accurate positioning.
Ask the skill to fill a PDF form by providing an input PDF and a fields.json mapping (or form field/value lists) so it produces a filled output PDF with annotations or form values.
High-intent search queries and answers about installing and using this skill.
To extract text and table data from PDFs, this skill uses pdfplumber-style parsing to read page text and layout structures. It reliably processes documents like invoices and reports to produce structured content for downstream automation workflows.
Filling non-fillable PDFs uses coordinate-based annotation workflows when interactive form fields are absent. The skill accepts a structured JSON input mapping fields and page coordinates to place text precisely and regenerate the form appearance.
Yes, you can merge, split, and rotate PDFs automatically using pypdf-based transformations. The skill handles document restructuring operations and metadata reading to create new merged or rotated PDF outputs.
The best way to convert PDF pages to images for coordinate mapping is using pdf2image and PIL. This skill supports optional image-coordinate workflows by converting PDFs to PNG, enabling precise visual annotation placement.
You need ImageMagick installed for image-coordinate workflows that require PDF-to-PNG conversion. Alongside pypdf and pdfplumber, it provides the rendering capabilities necessary to validate and place annotations accurately.
Yes, pypdf supports detecting existing interactive form fields. When fillable fields are available, the skill automatically populates them with values; otherwise, it guides coordinate-based annotation workflows for non-fillable templates.
zhang-ming-huiExtract text and tables, transform pages, and fill PDF forms.
automate-me7Extract text and tables from PDFs using pypdf and pdfplumber.
sigitpoerwoExtract text, merge, split, and fill PDF forms using Python libraries.
TakfesExtract text, tables, and metadata from PDF documents.
