AI SummaryUse this skill when the user wants fully local image generation with a pipeline and does not want online image APIs. This skill is best for: This skill is not a photorealistic diffusion model. It is a local, rule-based composition engine that renders through SVG and exports PNG locally.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "free-imagegen" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/free-imagegen && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/free-imagegen/SKILL.md "https://raw.githubusercontent.com/NimaChu/free-imagegen/main/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Fully local free text-to-image skill for OpenClaw and general assets. Generates SVG from prompt, then converts SVG to PNG with local tools only (no online API calls).
Free ImageGen
Use this skill when the user wants fully local image generation with a Prompt -> SVG -> PNG pipeline and does not want online image APIs. This skill is best for: • text-heavy cover images • Xiaohongshu-style text covers • infographics and knowledge cards • article-to-image card sets • OpenClaw thumbnails and icons • simple stylized illustrations as a lightweight fallback • direct custom_svg rendering when the agent wants full visual control This skill is not a photorealistic diffusion model. It is a local, rule-based composition engine that renders through SVG and exports PNG locally.
When To Use It
Use free-imagegen when the request matches one or more of these cases: • the user wants free local text-to-image generation • the user wants local PNG output, with optional SVG retention when needed • the user wants a text cover, title card, poster, or thumbnail • the user wants an infographic, comparison card, flow card, QA card, map, or catalog • the user wants to turn an article into a sequence of image cards • the user wants OpenClaw-ready thumbnail / icon assets Do not use this skill when the user needs: • photorealistic generation • inpainting / outpainting • model-based image editing • online hosted image APIs
Core Modes
Choose the mode from the user intent.
`illustration`
Use this only as a lightweight fallback for quick stylized subject prompts. Good for: • abstract or poster-like subject sketches • quick experiments when exact object fidelity does not matter • simple stylized compositions without dense text Avoid relying on illustration when the user wants a clearly recognizable: • person • animal • object • mascot • scene with specific visual requirements For those, prefer custom_svg so the agent can directly author the SVG instead of being constrained by the built-in illustration branch.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster