PixVerse Skills
Skills for an agent that makes video, images, speech and music through the PixVerse CLI using ready pipelines.
- 65 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The CLI signs in to a PixVerse account and spends paid credits on every generation.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/pixverse-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI signs in to a PixVerse account and spends paid credits on every generation.
This is third-party code. Review the repository files before installing.
What it does
The repository teaches an agent to work with the PixVerse CLI, the UI-free version of pixverse.ai. The main file `skills/SKILL.md` loads the right section: single commands live in `capabilities/` and multi-step scenarios in `workflows/`. Covered are text and image to video, image editing, speech, music, motion control, transitions, longer duration and upscaling, effect templates, MiniApps and Canvas graphs. Separate sections describe persistent characters and items, poster design and Seedance prompts. The agent learns which flags to pass, which model supports what and how to retry.
Who it is for. Video creators and media pipeline developers with a PixVerse subscription and an agent in Claude Code, Cursor or Codex.
Good fit when
- The agent makes a video from a text description and waits for the finished task.
- The same character recurs across scenes through a three-view sheet and an asset ID.
- An image becomes an animation, a keyframe transition or a longer clip.
- A Canvas graph is edited with a patch: dry run first, then apply.
Not a fit when
- You have no PixVerse subscription and the CLI is for paid users only.
- You need generation with another model or service.
- The agent must run offline without spending credits.
Example request
Make a five-second PixVerse video of an astronaut cat floating in zero gravity and wait for the finished file.Limitations
The PixVerse CLI spends the same credits as the website and is available only to subscribed users. The skills document CLI version 1.4.15, and older versions need the help of the installed command. Canvas and MiniApp schemas come from the live CLI, with a static model catalog as a fallback. Storyboarding needs ImageMagick and ffmpeg, and on Windows the helpers use PowerShell. Retry deliberately: every generation run spends credits, so the skills ask to review the task result before the next step.
How to disable. Delete the skills folder from the agent directory and, if you no longer need the CLI, run `npm uninstall -g pixverse`. Sign out through `pixverse auth`.
FAQ
How do I start with the PixVerse CLI?
Run `npm install -g pixverse` and then `pixverse auth login`. After that `pixverse create video --prompt "..." --json` starts generation.
How do I find which models and parameters exist?
`pixverse capabilities create --json` works offline and returns the catalog of the installed version. The Canvas catalog is queried separately.
Is login needed to browse capabilities?
No, `capabilities` and `capabilities create` work without login. `capabilities canvas` calls the service and requires it.
How do I wait for a MiniApp result?
Creation returns a `project_id`. Pass it to `pixverse task wait <project_id> --type miniapps --json`, then to `pixverse asset download`.
How do I run the repository tests?
With `python3 -m unittest discover -s tests -v`. They run without generating media or spending credits.
Discussion
No questions or reviews yet.
Related
SkillsA pixel art skill: the agent describes the art in code, and pxl builds PNGs, sprite sheets and GIFs and shows the painting live
Two skills for generative video and images: video writes Seedance, Kling and Veo prompts by dramaturgy rules, image picks the model and its syntax
Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
Scenario Agent Skills
scenario-labs-skills
Skills for the paid Scenario service: images, video, audio and 3D from an agent, model and price selection before spending, sets for game assets and brands
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
README in short
The skills add agent instructions to the PixVerse CLI: commands, model limits and scenarios. Persistent characters and items are stored as cloud assets and reused by ID.