- Home
- Skills
- Workflow Automation
- PDF Toolkit — Extract, Merge, Split, Fill, and OCR PDF Files
PDF Toolkit — Extract, Merge, Split, Fill, and OCR PDF Files
All major PDF operations: text/table extraction, merge, split, form fill, OCR, encryption
Free
Works with the AI Agents you already use
PDF Toolkit — Extract, Merge, Split, Fill, and OCR PDF Files
Example session with this skill installed
Merge doc1.pdf and doc2.pdf, rotate the first page 90 degrees, and save it as final.pdf.
- Read your context and instructions
- Compiled the pdf toolkit
I have generated the script to merge and rotate your files.
from pypdf import PdfReader, PdfWriter
writer = PdfWriter()
for f in ["doc1.pdf", "doc2.pdf"]:
reader = PdfReader(f)
for i, page in enumerate(reader.pages):
if f == "doc1.pdf" and i == 0:
page.rotate(90)
writer.add_page(page)
with open("final.pdf", "wb") as out:
writer.write(out)
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
PDF interaction often fails when standard libraries mishandle complex layouts, tables, or scanned content. Developers struggle with inconsistent text extraction, broken Unicode rendering, and the complexity of programmatic PDF creation.
What it does
- Extracts structured text and tabular data from documents into pandas DataFrames.
- Automates document operations including merging, splitting, rotating, and watermarking.
- Generates dynamic PDF reports from scratch using layout engines and markup.
- Performs OCR on scanned documents to convert images into searchable text.
- Manages document security through encryption, decryption, and password protection.
Frameworks & tools
Python (pypdf, pdfplumber, reportlab, pytesseract), CLI tools (qpdf, poppler-utils, pdftk).
Why this beats prompting it yourself
Programming PDF logic by hand often leads to encoding errors or failed table detection. This skill provides the specific syntax for layout-aware extraction and correctly handles delicate tasks like subscript rendering and OCR pipelines that generic prompts usually hallucinate.
Use cases
- Convert messy PDF invoices into clean Excel or CSV files.
- Batch process and watermark a directory of legal documents.
- Build automated reporting pipelines that generate multi-page branded PDFs.
- Remove passwords from restricted documents for automated ingestion.
Known limitations
ReportLab lacks native Unicode subscript/superscript support in default fonts. OCR requires external Tesseract and Poppler dependencies.
Based on the open-source skill from Anthropic's anthropics/skills repository (Apache-2.0). See NOTICE.md.
ReportLab cannot render Unicode subscript/superscript glyphs directly. OCR requires local installations of Tesseract and pdf2image dependencies.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
15 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
Requires