Agent skill · software engineering · mvanhorn
pp-openart
Generate videos and images on OpenArt from the terminal. Spend your existing OpenArt credits across Seedance, Kling,...
Why this skill is useful
Adds specific commands and workflows for generating images and videos using the OpenArt API that the AI wouldn't reliably generate on its own.
What it needs
Requires openart-pp-cli installed locally. About 8k tokens when loaded. Last updated 2026-08-06. 1,890 stars on the source repository.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT. This file is a verbatim mirror of library/ai/openart/SKILL.md, regenerated post-merge by tools/generate-skills/. Hand-edits here are silently overwritten on the next regen. Edit the library/ source instead. See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". --> Openart — Printing Press CLI Prerequisites: Install the CLI This skill drives the openart-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first: 1. Install via the Printing Press installer: 2. Verify: openart-pp-cli --version 3. Ensure $GOPATH/bin (or $HOME/go/bin) is on $PATH. If the npx install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish. If --version reports "command not found" after install, the install step did not put the binary on $PATH. Do not proceed with skill commands until verification succeeds. Spend your OpenArt credits programmatically. Generate videos with Seedance, Kling, Veo and more from the terminal. Unique Capabilities These capabilities aren't available in any other tool for this API. Generation video gen — Submit + poll + download videos in one command. image gen — Submit + poll + download images in one command. The Nano Banana family has two variants: nano-banana (50 credits, verified) and nano-banana-pro (120 credits, higher quality, experimental). There is no nano-banana-2 — Pro is the upgrade path. The other image models (gpt-image-2, gpt-image-1-5, flux-2-pro, byte-plus-seedream-4, byte-plus-seedream-4-5, google-imagen-4, qwen-image-max) are also experimental: their submit shapes were inferred from the JS bundle but not individually verified live, so they require --accept-experimental. Run openart-pp-cli models list --family image to see slugs, costs, and the experimental flag before picking. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mvanhorn/pp-openart