Edit PDF Text with Natural Language Using Nano Pdf

Nano Pdf lets you edit text inside existing PDFs by describing the change in plain English. You point it at a page and tell it what to fix, and it handles the rest. This is useful when you need to update a date, fix a typo, or change a name in a PDF without opening a full editor or re-creating the document from scratch.

What it does

Nano Pdf takes a PDF file, a page number, and a natural-language instruction, then modifies the text on that page according to your request. It works for targeted text edits like updating a title, correcting a client name, or adjusting a date. The tool runs as a command-line utility and is bundled with Hermes Agent, so it is available immediately after installation.

Before you start

Nano Pdf requires Python and either uv (recommended, already available in Hermes) or pip to install. It also needs an LLM API key to function; check nano-pdf --help for configuration details. The skill is available on Linux, macOS, and Windows.

Install it with one of these commands:

# Install with uv (recommended — already available in Hermes)
uv pip install nano-pdf

# Or with pip
pip install nano-pdf

Usage

The basic command structure is:

nano-pdf edit <file.pdf> <page_number> "<instruction>"

Examples

# Change a title on page 1
nano-pdf edit deck.pdf 1 "Change the title to 'Q3 Results' and fix the typo in the subtitle"

# Update a date on a specific page
nano-pdf edit report.pdf 3 "Update the date from January to February 2026"

# Fix content
nano-pdf edit contract.pdf 2 "Change the client name from 'Acme Corp' to 'Acme Industries'"

When not to use it

For structural PDF work like merging, splitting, filling forms, adding watermarks, or creating new PDFs, use the pdf skill instead. For extracting text from scanned documents, use ocr-and-documents. Nano Pdf is designed for text edits only, not for layout-heavy modifications.

Limits and gotchas

• Page numbering may be 0-based or 1-based depending on the version. If the edit lands on the wrong page, retry with the page number adjusted by ±1.
• Always verify the output PDF after editing. Use read_file to check file size, or open the file to confirm the change.
• The tool uses an LLM under the hood, so it requires an API key. Check nano-pdf --help for configuration options.
• It works well for text changes. Complex layout modifications may need a different approach.

Related skills

• pdf, for structural PDF operations (merge, split, forms, watermarks, creation)
• ocr-and-documents, for text extraction from scanned documents