Extract text and tables from PDFs using Python libraries.
npx skills add https://github.com/dtorras/dotfiles --skill pdf-dtorras
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/dtorras/dotfiles/tree/main/config/claude/skills/pdf Command: npx skills add https://github.com/dtorras/dotfiles --skill pdf-dtorras
PDFs often require repetitive manual data entry and data extraction, leading to errors and wasted time. This Skill automates common PDF tasks like filling forms, extracting text and tables, and composing results for reporting and archiving.
Provide a sample PDF and request automated extraction of text and form fields, with optional annotation and export to CSV.
High-intent search queries and answers about installing and using this skill.
Automate PDF text extraction using Python libraries like pypdf and pdfplumber to pull text and table data. Process batches of invoices by extracting key fields and compiling them into a CSV file for reporting and archiving.
Yes, you can fill both fillable and non-fillable PDF forms programmatically. The Skill automates form filling and digitization using Python libraries to render and annotate documents for administrative workflows.
Yes, pdfplumber supports extracting structured table data from mixed PDF types. The Skill handles both text-based and scanned PDFs using pdfplumber alongside pdf2image and Pillow to parse and render documents.
Handle scanned PDFs for data extraction by using pdf2image and Pillow to render pages before parsing. This approach enables reliable batch processing and archival data retrieval across mixed PDF types without repetitive manual entry.
Pypdf focuses on parsing and basic document composition rather than complex rendering. For advanced annotation or handling scanned documents, the Skill depends on pdfplumber, pdf2image, and Pillow to supplement pypdf's capabilities.
gerald-icaExtract text and tables from PDFs and fill forms using Python libraries.
UniquecreteMonitor a folder, extract receipt fields via the Zo API, and store them in SQLite.
MoshPitCodesExtract text and tables from PDFs using Python libraries.
jordanhubbardExtract text from PDFs, scanned documents, and images via OCR.
