Skip to main content
skill CX Codex

nano-pdf · swarmclawai — Claude Code skill: what it does, how to install

CLI-backed skill for editing and generating PDF files using plain-text instructions.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add swarmclawai/swarmclaw --skill nano-pdf -a claude-code
Open on GitHub

What nano-pdf does

This skill lets agents manipulate PDF documents via the nano-pdf CLI tool. It builds single-page documents from scratch with the create command or modifies text on targeted pages with edit.

The underlying nano-pdf binary must be installed on your system beforehand via uv tool install nano-pdf or pip install nano-pdf. The skill cannot run without it. Multi-page edits require a separate CLI call for each individual page. Page indexing can start at 0 or 1 depending on the tool release, so index adjustments by one are sometimes necessary.

What it helps with

  • generate a new PDF document from a text prompt
  • edit titles or fix typos on a specific PDF page
  • create single-page summaries with headers and bullet points
  • automate repetitive page-level PDF text adjustments

Example prompts for the agent

  • Create a one-page summary output.pdf with quarterly metrics and a footer
  • Edit deck.pdf page 1 to change the title to 'Q3 Results'
  • Fix the typo in the subtitle on page 2 of report.pdf

How to install nano-pdf

1Skills CLI (Vercel)

npx skills add swarmclawai/swarmclaw --skill nano-pdf -a claude-code

2Manually: put the files in place

~/.claude/skills/nano-pdf/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nano-pdf/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nano-pdf

How do I install nano-pdf in Claude Code?

Run npx skills add swarmclawai/swarmclaw --skill nano-pdf -a claude-code. You also need the CLI tool installed on your machine using uv tool install nano-pdf or pip install nano-pdf.

What does nano-pdf do?

It translates plain-language requests into CLI commands that generate new PDF files or apply text edits to existing PDF pages.

How are PDF pages indexed in nano-pdf?

Page indexing is either 0-based or 1-based depending on the tool version. If an edit lands on the wrong page, rerun the command adjusting the index by one.

Source text

SKILL.md · MIT
---
name: nano-pdf
description: Edit or create PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to make a PDF, edit a PDF, add pages, change text in a PDF, or convert content to PDF format.
metadata:
  {
    "openclaw":
      {
        "emoji": "📄",
        "requires": { "bins": ["nano-pdf"] },
        "install":
          [
            {
              "id": "uv",
              "kind": "uv",
              "package": "nano-pdf",
              "bins": ["nano-pdf"],
              "label": "Install nano-pdf (uv)",
            },
          ],
      },
  }
---

# nano-pdf

Use `nano-pdf` to apply edits to a specific page in a PDF using a natural-language instruction.

## Quick Start

```bash
nano-pdf edit deck.pdf 1 "Change the title to 'Q3 Results' and fix the typo in the subtitle"
```

## Creating a New PDF

```bash
nano-pdf create output.pdf "Create a one-page summary of quarterly results with a header, bullet points, and a footer"
```

## Usage in SwarmClaw

When a user asks to create or edit a PDF:

1. Check if `nano-pdf` is installed: `which nano-pdf`
2. If not installed, install via `uv tool install nano-pdf` or `pip install nano-pdf`
3. Run the appropriate command
4. Report the output file path to the user

## Notes

- Page numbers are 0-based or 1-based depending on the tool's version; if the result looks off by one, retry with the other.
- Always sanity-check the output PDF before reporting success.
- For multi-page edits, run separate commands per page.

© swarmclawai · MIT · swarmclawai/swarmclaw

Similar skills

All skills for Office documents →

nano-pdf by other authors comes first.

From the same set12

summarize This skill drives the summarize CLI so the agent can condense a web page, pull a YouTube transcript, or read text out of a local file. CX Codex +1 ★ 700repo stars skill-creator Builds, edits, and audits skills for AI agents. Useful when creating a skill from scratch or trimming an oversized SKILL.md file. CX Codex +1 ★ 700repo stars resourceful-problem-solving This skill gives coding agents a fallback plan for requests they cannot handle directly: look for an existing skill, find a command-line utility, or write a script. CX Codex +1 ★ 700repo stars openai-image-gen This skill generates images through the OpenAI Images API using GPT Image, DALL-E 3 or DALL-E 2. It also builds an HTML gallery of the results. CX Codex +1 ★ 700repo stars nano-banana-pro Generate images with Gemini 3 Pro Image, edit a single file, or combine several into one composition. You’ll need a Gemini API key. CX Codex +1 ★ 700repo stars google-workspace Teaches an agent to drive Google Workspace through the gws CLI: Drive files, docs, spreadsheets, mail, calendar and chat. Useful when a task touches a real Google account. CX Codex +1 ★ 700repo stars github Runs GitHub issues, pull requests, and CI checks via the gh CLI. Useful for triaging failed workflow logs or merging PRs directly from agent chats. CX Codex +1 ★ 700repo stars coding-agent Hands coding work to external agents for separate projects, PR reviews, and large refactors. Use it when the agent needs to inspect files and work through multiple iterations. CX Codex +1 ★ 700repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor