PixVerse Skills

Agent skill library for PixVerse CLI — helps AI agents (Claude Code, Cursor, Codex, etc.) generate videos, images, and audio (speech & music) through structured, composable workflows.

What is this?

PixVerse CLI is a UI-free version of pixverse.ai — all models, parameters, and capabilities from the website are available as CLI commands with structured JSON output.

This repository provides skill files that teach AI agents how to use those commands correctly: which flags to pass, which models support which parameters, how to chain commands into pipelines, and how to handle errors.

Quick Start

# Install the CLI
npm install -g pixverse

# Authenticate
pixverse auth login

# Create a video
pixverse create video --prompt "A cat astronaut floating in space" --json

PixVerse CLI uses the same credit system as the website. Only subscribed users can use it. See subscription plans.

Skill Structure

skills/
  SKILL.md                          # Entry point — start here
  capabilities/                     # Individual command skills
    auth-and-account.md             #   Authentication & account management
    create-video.md                 #   Text-to-video, image-to-video, fusion
    create-and-edit-image.md        #   Text-to-image, image-to-image
    create-voice.md                 #   Text-to-speech (TTS) — MiniMax, ElevenLabs voices
    create-music.md                 #   Prompt-to-music — MiniMax, ElevenLabs, Google Lyria
    modify-video.md                 #   AI content editing (replace subjects, swap outfits, change backgrounds)
    motion-control.md               #   Character animation with motion reference video
    transition.md                   #   Keyframe transition animations
    post-process-video.md           #   Extend duration, upscale resolution
    prompting-guide.md              #   Model-agnostic prompt advice (advice only — never auto-edits)
    prompt-enhance.md               #   Prompt optimization for V6 video generation
    seedance-prompt-optimize.md     #   Prompt optimization for Seedance 2.0
    seedance-vibe-creating.md       #   Vibe Creating — distill emotional / atmospheric ideas into Seedance 2.0 prompts
    task-management.md              #   Poll and wait for generation tasks
    asset-management.md             #   List, download, upload, delete assets
    saved-folders.md                #   Organize assets into named folders
    template.md                     #   Browse and create from effect templates
    workspace.md                    #   Team workspace management
    mondo-poster-design.md          #   Mondo-style poster, book cover, album art design
    character-design.md             #   Persistent characters — three-view sheet + cloud asset id reuse
    item-design.md                  #   Persistent items / props — four-panel orthographic sheet + cloud asset id reuse
  workflows/                        # Multi-step pipeline skills
    text-to-video-pipeline.md       #   End-to-end text-to-video
    image-to-video-pipeline.md      #   Animate an image into video
    text-to-image-to-video.md       #   Generate image then animate it
    image-editing-pipeline.md       #   Iterative image editing
    modify-video-pipeline.md        #   Modify video content then enhance
    motion-control-pipeline.md      #   Character animation end-to-end
    video-production.md             #   Full production (create + extend + audio + upscale)
    storyboard-to-video.md          #   Multi-shot storyboard → concatenated video
    batch-creation.md               #   Parallel batch generation
    mondo-poster-pipeline.md        #   End-to-end Mondo poster generation
    mondo-poster-to-video-pipeline.md #  Animate poster into cinematic video
  references/                       # Curated design knowledge
    mondo-poster/                   #   37 artist styles, composition, genre templates

Capabilities vs Workflows

• Capabilities document a single command or command group — flags, models, parameter constraints, JSON output format, error codes.
• Workflows compose multiple capabilities into end-to-end pipelines with step-by-step instructions.

Supported Models

Video Models

Image Models

Voice / TTS Models

Music Models

For AI Agent Developers

These skills are designed to be loaded into agent context. Each skill file is self-contained with:

• Decision trees — help the agent choose the right command
• Flag tables — every parameter with allowed values and defaults
• Model reference tables — per-model parameter constraints
• JSON output schemas — exact response format for parsing
• Exit codes — deterministic error handling
• Examples — copy-paste-ready commands

Start by loading skills/SKILL.md as the entry point, then load specific capability or workflow skills as needed.

Community Skills

Projects built on top of PixVerse CLI by the community:

Have a project built on PixVerse CLI? Open a PR to add it here.

Credits

Thanks to the creators whose work has contributed to the PixVerse ecosystem:

• @takamasa045 — for building character pipeline and shotpack production tools on PixVerse CLI
• @vista8 — for the Mondo poster design system whose prompt engineering and artist style library are adapted in pixverse:mondo-poster-design

Links

• PixVerse Website
• PixVerse CLI on npm
• Subscription Plans