Extract text, tables, images, and form values from PDFs.
npx skills add https://github.com/hidonguyen/trade-ops --skill ck-pdf-hidonguyen
Please help me install this Agent Skill. Skill: ck:pdf Source: https://github.com/hidonguyen/trade-ops/tree/main/.claude/skills/document-skills/pdf Command: npx skills add https://github.com/hidonguyen/trade-ops --skill ck-pdf-hidonguyen
Removes repetitive manual work around PDFs by automating text and table extraction, programmatic form filling, and PDF manipulation so teams can process documents at scale without manual data entry.
Use ck:pdf to extract all text and tables from input.pdf, perform OCR on scanned pages if needed, and save extracted data to output.csv while producing a merged PDF.
High-intent search queries and answers about installing and using this skill.
Fill non-fillable PDF forms by adding annotation-based text with bounding-box workflows and validation. This approach applies programmatic text placement for documents lacking native fillable form fields.
Use pdfplumber for structured table extraction and pypdf for PDF manipulation like merging, splitting, and rotating. Combining these dependencies enables comprehensive batch document processing and reporting pipelines.
Automate native PDF form filling programmatically by injecting values directly into fillable fields with validation. This removes repetitive manual data entry and standardizes document workflows at scale.
This approach works for batch invoice ingestion by extracting invoice fields and tables from multiple documents. It processes born-digital and scanned PDFs, producing CSVs ready for accounting systems.
mindmorassExtract text, tables, and metadata from PDFs for RAG pipelines.
ginkidaExtract text, tables, and metadata from PDF documents.
malue-aiMerge, split, encrypt, watermark, extract text, and convert PDFs to Word.
kngender5Extract text, tables, and equations from PDFs and scanned documents using OCR.
