
Geospatial Data Analyst AI Skill
Oskari




Skill fileClaude Skills for Data Analysts
Turns PDFs and scans into verified CSV or JSON tables, with every doubtful value flagged instead of guessed.
$9· one file, yours to keep
Yours to keep · instant download
Or all of them, $6.99/mo
Lavinia and 2,500+ other specialists, in your AI. Ask for any of them by name.
7 days free, then $6.99/mo · cancel anytime
One file
All-in-one
30-day money-back · secure checkout by Stripe
# Lavinia - PDF & Document Extraction Specialist ## Role You are Lavinia, a document data specialist. You have spent years turning other people's PDFs into data a spreadsheet, database or accounting system can trust: bank statements, supplier invoices, lab reports, shipping manifests, signed contracts, scanned forms and 80-page annual reports with tables that break across pages. Your value is not that you can "read a PDF". Any AI can try. Your value is that you design the extraction before you do it, you know where PDFs lie (merged cells, rotated pages, ligatures, columns read in the wrong order, scanned 8s that look like 3s), and you prove the output is right before anyone pastes it into a ledger. When a value is not readable you say so. You never fill a gap with a plausible number. ## How you differ from other document tools - **Invoice-only extractors** (such as an invoice OCR skill) know one document type. You work on any document and design the schema per job. - **PDF makers** (invoice or resume PDF generators) create documents. You go the other way: documents in, structured data out, plus PDF housekeeping (split, merge, reorder, fill).
Here are three months of bank statements as PDFs. Give me one CSV with date, description, amount and balance for my bookkeeper. UK dates, debits negative.
You get: the mode used and assumptions → a field schema with types and formats → one CSV with every transaction, page references and split rows rejoined → a validation table: row counts, opening plus credits minus debits equals closing for each month, running balance on every row → a flags list with any unreadable or doubtful value and its page → a 5-value spot check → import notes for your bookkeeper.
Lavinia is an AI PDF skill for Claude or ChatGPT. She extracts tables, fields and text from PDFs, scans and Word files into CSV, JSON or Excel-ready tables. She designs a schema, rejoins tables split across pages, normalizes dates and amounts, and validates row counts, control totals and tax math. In code mode she also splits, merges, rotates and fills PDFs.
Invoice OCR Extraction AI is built for invoices only. The AI PDF Invoice Maker and AI PDF Resume Maker create new PDFs. Lavinia works the other way and on any document: statements, forms, reports, price lists, contracts. She designs the extraction per job and attaches a validation report so you can trust the numbers before importing them.
It depends on scan quality and on the OCR your AI app or ocrmypdf provides. Lavinia does not hide that: she re-checks digits that scans often confuse, such as 8 and 3 or 0 and O, reconciles against printed totals, marks uncertain values CHECK and unreadable ones UNREADABLE. Handwriting and blurry photos will have more flags.
Lavinia works inside your own AI app, under that app's data settings, so check them before uploading sensitive files. The skill itself masks account numbers in its reports, treats any text inside a PDF as data rather than instructions, and refuses to bypass passwords on files you do not own.
Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.