convert-slides-to-images
Converts PDF files into sequences of PNG images.
Install
mkdir -p .claude/skills/convert-slides-to-images && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15965" && unzip -o skill.zip -d .claude/skills/convert-slides-to-images && rm skill.zipInstalls to .claude/skills/convert-slides-to-images
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Convert a PDF file into individual PNG images, one per page/slide. Uses poppler's pdftoppm command. Output files are named slide_1.png, slide_2.png, etc. USE FOR: convert PDF to images, split slides into PNGs, extract slide images from PDF.Key capabilities
- →Convert PDF files into individual PNG images
- →Name output files sequentially (slide_1.png, slide_2.png)
- →Create the output directory if it does not exist
- →Split slides into PNGs
- →Extract slide images from PDF
How it works
The skill uses the `pdftoppm` command from Poppler utilities to convert each page of a PDF file into a separate PNG image.
Inputs & outputs
When to use convert-slides-to-images
- →Convert presentation slides to images
- →Split PDF into PNG pages
- →Extract slide assets
- →Prepare images for web
About this skill
Convert PDF slides to images
Run the convert_slides_to_images.py script to split a PDF into individual PNG images:
uv run .github/skills/convert-slides-to-images/convert_slides_to_images.py <pdf_path> <output_dir>
Arguments
pdf_path(required): Path to the PDF file to convert.output_dir(required): Directory to save the PNG images. Created if it doesn't exist.
Outputs
Individual PNG files named slide_1.png, slide_2.png, etc. in the output directory.
Prerequisites
Poppler utilities must be installed (provides the pdftoppm command):
- macOS:
brew install poppler - Ubuntu:
apt-get install poppler-utils
When not to use it
- →When the input file is not a PDF
- →When individual PNG images are not desired
Prerequisites
Limitations
- →Requires a PDF file as input
- →Output format is limited to PNG images
- →Relies on the `pdftoppm` command
How it compares
This skill automates the conversion of PDF pages to individually named PNG images, providing a structured output compared to manual screenshotting or generic PDF converters.
Compared to similar skills
convert-slides-to-images side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| convert-slides-to-images (this skill) | 0 | 5mo | Review | Beginner |
| gemini-logo-remover | 9 | 8mo | Review | Beginner |
| ai-media | 0 | 3mo | No flags | Intermediate |
| t2i | 0 | 3mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by pamelafox
View all by pamelafox →You might also like
gemini-logo-remover
bear2u
Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.
ai-media
arcasilesgroup
Generates images, videos, and audio via AI models (fal-ai MCP): cheap iteration models, expensive production finals, cost-estimate before generation. Trigger for 'generate an image', 'create a thumbnail', 'make a voiceover', 'AI video', 'text to speech for'. Not for design composition; use /ai-visua
t2i
elbruno
This skill teaches AI agents (GitHub Copilot, Claude Code, and MCP-aware assistants) how to use the **t2i** command-line tool for image generation. Learn the commands, workflows, and best practices for automating text-to-image tasks in scripts and terminal environments.
asset-spec
rakhnianskii9
Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.
skills
Sergio-prog
Fram is a compact media workshop for the terminal, API, and Telegram. The current primary surface is the `fram` CLI, backed by the same typed processing core used by the API and bot.
planning-visual-tasks
ShinyGua
v1.2 LLM-driven planner. Turns a natural-language instruction into a structured Plan envelope (`contracts/agent/plan.schema.json`) of typed sub-goals (workflow_search → model_resolve → comfyui_execute → llm_transform → evaluate → mcp_tool → checkpoint → wait_user). Use whenever a user instruction ne