Claude Skills for PDFs: Extract, Merge, and Fill Forms Automatically

PDF was designed to look the same on every screen and every printer — not to give up its data easily. That single design choice is the source of a remarkably universal set of frustrations: copy-paste that garbles text, tables that lose their columns, scanned documents where the text is visible but not selectable, and forms that have to be filled out one tedious field at a time. Almost everyone who works with documents hits one of these problems eventually, and almost none of it requires real technical skill to fix once the right tool is doing the work.

These four Claude Skills cover the PDF tasks that come up over and over — pulling structured data out, combining or splitting files, filling forms in batch, and making scanned documents searchable again.

Skill 1: Get Clean Data Out of a Document Built for Printing

The data you need is trapped in a two-hundred-page PDF, and a basic copy-paste gives you garbled text with tables that lose their structure entirely — numbers ending up in the wrong columns, rows merging together, headers disappearing. The PDF was designed to be printed and read, not to hand its data back out in a usable form.

The PDF Text & Table Extractor Skill uses pdfplumber for precise, character-level extraction rather than a basic text dump: clean CSV files for every table detected, full text extraction with page numbers preserved, document metadata, and a summary of exactly what was found and where.

⏱ Setup takes about 10 minutes. Works especially well on financial statements, research papers, and reports with dense tabular data.

Skill 2: Merge and Split Without a Subscription

Combining eight PDF attachments into a single file for a submission, or splitting a hundred-page document into individual chapters, is exactly the kind of task that comes up often enough to be annoying but rarely enough that paying for Adobe feels justified. Free online tools work until they don't — file size limits, watermarks, or upload restrictions that turn a thirty-second task into a frustrating search for a tool that'll actually handle the file.

The PDF Merge & Split Tool Skill handles both directions locally: merging multiple PDFs into one file with bookmarks and a generated table of contents, or splitting a large document into separate files while preserving page numbering throughout.

⏱ Setup takes about 10 minutes. Runs locally on your files — no upload size limits or subscription required.

Skill 3: Fill Dozens of Identical Forms From a Spreadsheet

Fifty identical PDF forms with different data for each one — government paperwork, insurance claims, vendor onboarding — typed by hand, one at a time, where a single typo means printing the page again and starting over. This is the specific kind of tedious, error-prone, repetitive task that a computer should be doing and almost never is, because most people don't know PDF forms can be filled programmatically at all.

The PDF Form Auto-Filler Skill fills a batch of forms directly from a spreadsheet: each PDF populated programmatically from the corresponding row of data, field validation catching missing or malformed entries before anything gets submitted, completed forms saved both individually and as a merged batch, and the filled data extracted back out as a verification spreadsheet.

⏱ Setup takes about 10 minutes. Ideal for HR onboarding, insurance claims, tax forms, and any recurring paperwork with the same fields across many records.

Skill 4: Turn a Scanned Image Back Into Searchable Text

Someone scanned a fifty-page contract and emailed it as a PDF — the text is visible, but it can't be selected, searched, or copied, because it's not text at all, it's a digital photograph of paper. Finding a single clause in a document like that means reading every page manually, and pulling a quote out means retyping it by hand.

The PDF OCR Scanner Skill runs optical character recognition on scanned or image-based PDFs and adds a real, selectable text layer on top: searchable keywords throughout the document, high character accuracy, and the extracted text also saved as a separate editable Word document for anyone who needs to work with the content directly rather than the scanned image.

⏱ Setup takes about 10 minutes. Especially valuable for legal document digitization, scanned receipts, and archival collections.

Matching the Skill to the PDF Problem in Front of You

Each of these four Skills solves a distinct, self-contained PDF problem rather than being stages of one pipeline:

• Need the data, not the document — PDF Text & Table Extractor for clean CSVs and structured text
• Need to combine or break apart files — PDF Merge & Split, no subscription or size limits
• Need the same form filled many times with different data — PDF Form Auto-Filler, driven from a spreadsheet
• Have a scan instead of a real document — PDF OCR Scanner, to make it searchable and copyable again

Some workflows naturally chain them — OCR a scanned form first, then extract the data, or merge a set of forms after filling each one individually — but each Skill stands on its own for the specific, universal PDF frustration it's built to solve.