Extract text, tables, and structured data from PDF documents.
npx skills add https://github.com/NickCrew/claude-cortex --skill pdf-nickcrew
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/NickCrew/claude-cortex/tree/main/skills/document-skills/pdf Command: npx skills add https://github.com/NickCrew/claude-cortex --skill pdf-nickcrew
This Skill eliminates the tedious manual work of filling out PDF forms and extracting data from documents, saving you hours of repetitive effort.
Extract all text from the attached file 'invoice-q3.pdf' using the pdf skill.
Use the pdf skill to determine if the attached document 'application.pdf' has fillable form fields or requires visual analysis for annotation placement.
Check if the PDF 'form.pdf' has fillable form fields by running the check_fillable_fields.py script from the skill's scripts directory.
High-intent search queries and answers about installing and using this skill.
Text and table extraction from PDFs is automated by reading document content using libraries that parse PDF structure. This Skill applies pdfplumber and pypdf to extract text, tables, and structured data from any PDF, enabling batch processing of large document sets like invoices or reports into usable formats such as CSV.
Programmatic form filling works by writing field values directly into fillable form fields or annotating non-fillable forms with visual positioning. This Skill handles both fillable and non-fillable PDFs with field metadata handling, bounding-box validation, and annotation-based filling to automate complex government or legal forms at scale.
Scanned PDF text extraction requires OCR processing to recognize text from image content. This Skill applies OCR capabilities to scanned pages alongside traditional text extraction, enabling you to recover data from image-based documents that lack embedded text layers.
Page manipulation—merging, splitting, and rotating—is handled by libraries that modify PDF structure and content ordering. This Skill supports page rotation, merging, and splitting operations to reorganize multi-page documents and extract specific sections without manual editing.
Batch processing large document sets is designed into this Skill through automated extraction, validation, and export workflows. It handles 100+ vendor invoices, applications, or similar documents in a single workflow, extracting fields like invoice number, date, and totals into compiled CSV files or databases.
PDF generation and watermarking are supported through reportlab and pypdfium2 libraries, enabling creation of new documents from scratch and addition of watermarks or annotations. This Skill covers both reading and writing PDFs for complete document automation workflows.
metaid-developersExtract text and tables from PDFs using pypdf and pdfplumber.
Datus-aiGenerate JSON, CSV, or markdown reports from SQL query results.
MaciWPQueue and schedule background tasks with Celery cron-style jobs.
nimadorostkarExtract text and structured data from PDFs with OCR for scanned images.
