PDF Field Extractor
Paste the following prompt into your AI chat to install this skill:
Please install @user_26bdbd50/pdf-field-extractor according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Many office PDFs keep structured data locked inside layouts, tables, and scanned pages: invoice totals, contract terms, business license fields, bank statement balances, and receipt line items. Manual transcription is slow and easy to get wrong. Pdf Field Extractor targets this workflow by extracting key document fields into machine-readable Excel or JSON files for reconciliation, archiving, or downstream import.
How It Works
- Locate content first:
PyMuPDFandpdfplumberextract text and tables; when a PDF has no text layer,pytesseractOCR is triggered, with support for Chinese, English, Japanese, Korean, and other languages. - Classify the document: keyword signals plus AI-based judgment identify invoices, contracts, receipts, business licenses, bank statements, courier notes, or general documents.
- Emit structured output: an OpenAI-compatible LLM call extracts fields, then the skill writes one record per row to
.xlsx, or preserves nested structure inJSON; batch runs merge the results.
Boundaries
- Users must provide their own LLM API key; the skill does not store it.
- Scanned PDF quality depends on image clarity; higher resolution and denoising improve OCR accuracy.
- It fits documents with stable fields such as invoices and contracts; free-form extraction quality depends on the chosen model and prompts.
Use Cases
- Finance receives a batch of PDF invoices and needs to extract invoice number, date, amount, buyer, and seller into Excel.
- Legal reviews contract PDFs and needs to extract parties, amount, term, and breach clauses into JSON for import.
- Operations organizes PDF courier notes and receipts and needs to batch extract tracking numbers, sender/receiver, and amount into a spreadsheet.
- Data analysts process PDF bank statements and need to extract dates, descriptions, debit/credit amounts into structured JSON.
Best For
- Finance teams that reconcile monthly PDF invoices and need to extract billing fields into Excel for reimbursement and auditing.
- Legal assistants who process contract PDFs and need key clauses exported as JSON for approval systems.
- E-commerce operators who batch-process PDF courier notes and receipts into standardized, filterable spreadsheets.
- Data analysts who clean PDF bank statements and need structured JSON output for reporting pipelines.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Turn a topic, notes, or tables into a complete PPT plan with logic, page layouts, visual and chart guidance, and natural defense scripts.