Convert Pdf To Png

Community

yrom

convert-pdf-to-png

Use when needing to convert PDF pages to PNG images for preview, comparison, or image processing.

Overview

Publisher	yrom
Repository	`arxiv-paper-translator`
Skill name	`convert-pdf-to-png`
Stars	57
Forks	3
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by yrom on GitHub. Read the source before you install it.

Installation

Install the Convert Pdf To Png AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/yrom/arxiv-paper-translator/tree/main/skills/convert-pdf-to-png
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/yrom/arxiv-paper-translator.git /tmp/arxiv-paper-translator
mkdir -p .claude/skills
cp -r /tmp/arxiv-paper-translator/skills/convert-pdf-to-png .claude/skills/convert-pdf-to-png

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Convert Pdf To Png in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Convert Pdf To Png on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Convert Pdf To Png is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Convert PDF to PNG

Convert PDF file pages to PNG images.

Backend Selection

Try system tools first (better rendering for complex PDFs), fall back to the JS script.

Backends you can try:

magick (ImageMagick) - Linux/MacOS
mutool (MuPDF) - Linux/MacOS
pdftoppm (Poppler) - Linux/MacOS
sips (Scriptable Image Processing System) - MacOS Only
JS fallback (pdfjs) - under <CURRENT_SKILL_DIR>/scripts/ directory.

NOTICE: All backends should output <pdf-name>_page_<N>.png in the target directory.

System Backend Examples

bash
# magick (ImageMagick) — density 144 ≈ scale 2x (72 * 2)
magick -density 144 paper.pdf -quality 90 paper_page_%d.png
# Note: magick outputs 0-based index; rename if 1-based is needed

# mutool (MuPDF) — resolution 144 ≈ scale 2x
mutool convert -o paper_page_%d.png -O resolution=144 paper.pdf

# pdftoppm (Poppler) — -r sets DPI
pdftoppm -png -r 144 paper.pdf paper_page
# Outputs paper_page-1.png, paper_page-2.png, etc.

# sips (macOS only) — convert a single-page PDF
sips -s format png paper.pdf --out paper_page_1.png

Different backends produce slightly different filename patterns (0-based vs 1-based, padding, separator). Rename after conversion if the downstream consumer requires strict <pdf-name>_page_<N>.png format.

JS Script Prerequisites

Dependencies are in <CURRENT_SKILL_DIR>/scripts/package.json. Install on first use:

bash
cd skills/convert-pdf-to-png/scripts && bun install 
# or npm install

JS Script Quick Start

bash
SCRIPT_DIR=skills/convert-pdf-to-png/scripts

# Convert all pages (default scale: 2.0x)
bun $SCRIPT_DIR/convert-pdf-to-png.mjs paper.pdf

# Specify output directory
bun $SCRIPT_DIR/convert-pdf-to-png.mjs paper.pdf --output-dir ./output

# Convert specific pages with higher resolution
bun $SCRIPT_DIR/convert-pdf-to-png.mjs paper.pdf --pages 1,3,5 --scale 3

# Encrypted PDF
bun $SCRIPT_DIR/convert-pdf-to-png.mjs protected.pdf --password "secret"

JS Script CLI Options

Option	Default	Description
`--output-dir <dir>`	Same as PDF	Output directory for PNG files
`--scale <number>`	`2.0`	Viewport scale factor (higher = better quality, larger files)
`--pages <list>`	all	Comma-separated 1-based page numbers
`--password <string>`	-	Password for encrypted PDF

Output

Filenames follow the pattern: <pdf-name>_page_<N>.png

Common Issues

Issue	Solution
Complex figures render as blank (pdfjs)	Use `magick` (ImageMagick) or `mutool` (MuPDF) instead
`Cannot find module 'pdf-to-png-converter'`	`cd skills/convert-pdf-to-png/scripts && bun install`
Poor text quality	Increase `--scale` / DPI (try 3.0 / 216)
Large PDF causes OOM	Convert specific pages with `--pages` instead of all
Encrypted PDF fails	Provide `--password` (JS) or `-p` (mutool) / `-upw` (pdftoppm)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/convert-pdf-to-png.mjs4 KB
scripts/package.json1 KB

Frequently asked questions

What does the Convert Pdf To Png AI skill do?

Use when needing to convert PDF pages to PNG images for preview, comparison, or image processing.

Why use Convert Pdf To Png on TypingMind?

Because you install it once and use it with any model. Convert Pdf To Png is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Convert Pdf To Png in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yrom/arxiv-paper-translator/tree/main/skills/convert-pdf-to-png. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Convert Pdf To Png?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Convert Pdf To Png?

As many as you like. As long as a model supports skills, you can use Convert Pdf To Png with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Convert Pdf To Png AI skill free?

Yes. It is published on GitHub by yrom under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Comps Analysis

NousResearch

OrganizationPopular

Build comparable-company valuation workbooks in Excel.

Lbo Model

Build leveraged buyout workbooks with IRR/MOIC in Excel.

Pptx Author

Build PowerPoint decks headless with python-pptx.

Pokemon Player

Play Pokemon via headless emulator + RAM reads.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Convert PDF to PNG

Backend Selection

System Backend Examples

JS Script Prerequisites

JS Script Quick Start

JS Script CLI Options

Output

Common Issues

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now