Extract text and structured tables from PDF documents.
npx skills add https://github.com/papachong/RHClaw --skill pdf-papachong
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/papachong/RHClaw/tree/main/RHClaw-Desktop/src-tauri/skills/pdf Command: npx skills add https://github.com/papachong/RHClaw --skill pdf-papachong
Many workflows rely on information trapped in PDFs — scanned receipts, invoices, reports, and fillable forms — and extracting, editing, or programmatically filling those documents by hand is slow, error-prone, and hard to scale. This Skill provides reproducible, scriptable operations to extract text and tables, perform OCR on scanned pages, fill and flatten forms, and merge or split documents to automate those tasks.
Extract all tables and text from invoices.pdf and combine them into a single CSV named invoices.csv.
High-intent search queries and answers about installing and using this skill.
To extract tables and text from PDF documents, you can parse born-digital pages using pdfplumber and pypdf to retrieve structured table data and raw text for downstream processing. Scanned PDFs require OCR via pytesseract to recover text.
You can batch extract invoice data from PDFs into a CSV file by scripting text and table extraction operations with pdfplumber and pypdf. This automates the retrieval of invoice data from multiple PDF sources and aggregates it into a single CSV output.
The best way to programmatically fill and flatten PDF forms is to use a scriptable tool that populates fillable and template-based PDFs, optionally flattening or encrypting the results. This automates form completion and secures the final output for distribution.
OCR works on scanned PDFs to recover text by converting pages to images with pdf2image and applying pytesseract. This OCR-based recovery extracts text from scanned receipts and invoices, making it available for downstream data analysis workflows.
To merge, split, and watermark PDF files for distribution, you can use command-line tools like qpdf alongside programmatic libraries. This allows you to combine multiple sources, split pages, rotate, and apply watermarks or password protection to output documents.
Limitations of pypdf and pdfplumber for PDF text extraction include difficulty parsing scanned documents without OCR, as these libraries primarily target born-digital PDFs. Scanned pages must be converted to images and processed via pytesseract to recover text effectively.
dakesanExtract text and tables from PDFs using Python libraries and CLI tools.
alibabaExtract text, tables, and metadata from PDF documents into JSON.
EnztunAutomate Excel spreadsheet operations with Python libraries like openpyxl, pandas, and matplotlib.
taracodlabsExtract readable text from PDFs, scanned images, and Word documents using Python libraries.