Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added metadata to SKILL.md for environment variables, required binaries, and homepage. - Updated the "Prerequisites" and "Workflow" sections for improved clarity; removed reference to the dependency check script and now instruct users to manually ensure dependencies are installed. - Minor rewording and formatting improvements throughout documentation. - Added .DS_Store file; removed evals/evals.json file.
What This Skill Does
nano-pdf converts PDF pages to images, sends them to Google's Gemini 3 Pro Image with your edit instructions, then stitches the AI-edited pages back into a PDF with OCR text layer restoration. It supports modifying existing pages and inserting new AI-generated slides that visually match the rest of the deck.
Unlike manual PDF editors that require pixel-level changes, nano-pdf accepts plain-text descriptions and uses AI to render visual edits directly on the page.
When to use it
- Fixing a typo on a specific slide in a presentation deck
- Updating chart data or numbers in a PDF report
- Rebranding slides with new colors and logos across multiple pages
- Adding a new title or summary slide to an existing PDF
- Changing header text or background color on selected pages
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: fix the typo on slide 5 and change the header background to dark blue on slide 1
- 1Verify nano-pdf, poppler, tesseract, and GEMINI_API_KEY are available
- 2Identify target pages (1 and 5) and write a focused prompt for each change
- 3Run: nano-pdf edit deck.pdf 1 "Change header background to dark blue" 5 "Fix 'recieve' to 'receive'"
- 4Present the output file edited_deck.pdf to the user
A PDF with the header background updated to dark blue on slide 1 and the typo corrected on slide 5
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.