Scenario 3D Worlds — model skill for 3D scenes
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
Walkable 3D worlds as Gaussian splats from text, a photo, a panorama or a video: Marble, HY World and TripoSplat.
- Type: Model · 3D scenes
- Slug:
scenario-3d-worlds - Status: live
- Publisher: Scenario (vendor)
- License: MIT
- Source: https://github.com/scenario-labs/skills/tree/main/skills/scenario-3d-worlds
- Works in: Claude Code, Codex, Cursor, Gemini CLI, Any MCP client
- Requires: Scenario account with credits (OAuth through the MCP, or an API key), Scenario MCP server (https://mcp.scenario.com/mcp)
- Cost: Billed in Scenario credits; Marble tiers differed more than tenfold in cost, so dry-run first
- Adoption: 807 installs, 3,658 GitHub stars (skills.sh, 2026-11-10)
What it does
Scenario's skill for explorable environments as 3D Gaussian splats rather than meshes. It picks the model by what you have: World Labs Marble (1.0 Draft, 1.1 and 1.1 Plus) for text, one image, 2–8 photos or a walkthrough video; HY World's image-to-skybox then skybox-to-splat pipeline for one photo of a place, and multi-view-to-splat for many overlapping photos; TripoSplat for a single object. The workflow iterates on Marble Draft with a fixed seed, then reruns the same parameters on a higher tier, and exports .spz. Splats make backdrops for world fly-throughs and previs; they have no UVs or editable topology.
Use when
- an explorable 3D world from a text idea or one image
- a 360 panorama or skybox turned into a walkable splat
- reconstruct a scene from 2–64 photos or a walkthrough video
- one product or object photo to a splat (TripoSplat)
- graybox a level or set from a concept image, then upgrade the same seed
Not for
- Polygon meshes, rigging or UVs: use scenario-3d
- A skybox with no splat stage: use scenario-skyboxes
Install
- Claude Code:
npx skills add scenario-labs/skills --skill scenario scenario-3d-worlds -a claude-code && claude mcp add --transport http scenario https://mcp.scenario.com/mcp - Codex:
npx skills add scenario-labs/skills --skill scenario scenario-3d-worlds -a codex - Cursor:
npx skills add scenario-labs/skills --skill scenario scenario-3d-worlds -a cursor - Gemini CLI:
npx skills add scenario-labs/skills --skill scenario scenario-3d-worlds -a gemini-cli - Any MCP client:
https://mcp.scenario.com/mcp - Any agent, with the vargai CLI:
vargai install scenario-3d-worlds
More 3D scenes skills
- Turn a brief into a Blender film written in Python: A brief becomes a Blender film from one Python file: shots as data, stills first, critic loop, Eevee or Cycles.
- Turn a browser game into a cinematic trailer: Record the browser game your agent built frame-exact, script shots and cameras, then cut a 1080p trailer on the beat.
- Blender Lab MCP Server: Blender's official MCP server: query and edit open scenes with Blender Python, bundled API docs and screenshots.
- Meshy 3D Generation: Meshy's official skill: text or image to a textured 3D model, then remesh, rig, animate and export it as GLB or FBX.
- Roblox Studio MCP Server: The MCP server built into Roblox Studio: agents edit scripts, run Luau, generate meshes and playtest your game.
- Unreal Engine Skills for Claude Code: Epic's official plugin: Claude Code drives a live Unreal Editor over MCP, from actors and materials to Sequencer.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Any agent with a terminal:
curl -fsSL https://varg.ai/install | sh(Windows:irm https://varg.ai/install.ps1 | iex), thenvargai loginand every model is a command —vargai generate_video …,vargai estimate_cost …(https://varg.ai/how-to/cli/) - Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt