skills.rest
Geuan666
Geuan666COMMUNITY
Explore all skills by this author →
GitHub

robotwin-image-to-env

Convert a single image into a draft RoboTwin environment with tabletop objects and anchors.

Updated Mar 8, 2026
Search Tags:#rendering#robotwin#image-to-env#asset-matching#tabletop-localization#pose-preset
One-click install
npx skills add https://github.com/Geuan666/skills-robotwin --skill robotwin-image-to-env
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: robotwin-image-to-env
Source: https://github.com/Geuan666/skills-robotwin/tree/main/robotwin-image-to-env
Command: npx skills add https://github.com/Geuan666/skills-robotwin --skill robotwin-image-to-env

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, Pillow, numpy, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This skill converts a single image into a reviewed RoboTwin environment by detecting visible tabletop objects, matching assets from a built-in library, localizing anchors on the tabletop with locate MCP, drafting the layout, and generating a renderable first frame.

Core Features & Use Cases

  • Object discovery on the tabletop using qwen3-vl-plus, followed by per-object cropping.
  • Asset candidate retrieval from the built-in multimodal asset library via qwen3-vl-embedding, with instance-level or class-level matching.
  • Pose preset selection per object using asset docs, then authoritative localization via locate-tabletop-contacts MCP.
  • Estimation of a conservative tabletop footprint and projection into a RoboTwin layout, followed by a render pass and VLM-based refinement.
  • Honest reporting for unresolved objects and generation of a draft RoboTwin env for user review.

Quick Start

Provide a source image; the system will generate a draft RoboTwin env and a first render for review.

Frequently Asked Questions about robotwin-image-to-env

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a tabletop image into a RoboTwin environment?▼

RoboTwin environment generation from an image identifies visible tabletop objects, matches assets from a built-in library, localizes contacts, drafts the layout, and produces a renderable first frame for user review.

What is the process for matching 3D assets to objects in a tabletop scene?▼

Asset matching for tabletop reconstruction uses qwen3-vl-plus for object discovery and cropping, then retrieves instance-level or class-level asset candidates from a built-in multimodal library using qwen3-vl-embedding.

Can I use this skill if some objects in my image are not in the asset library?▼

If objects are unresolved during asset matching, the skill provides honest reporting for those items while still generating a draft RoboTwin environment and a renderable first frame from the successfully matched objects.

How does tabletop localization work when generating a RoboTwin env from a picture?▼

Tabletop localization for layout projection applies per-object pose presets from asset docs, then uses the locate-tabletop-contacts MCP to estimate a conservative tabletop footprint and project anchors into a RoboTwin layout.

Does RoboTwin image-to-env handle renderable layout drafting for tabletop reconstruction?▼

RoboTwin env drafting from an image projects a conservative tabletop footprint into a layout, performs a render pass, and applies VLM-based refinement to produce a renderable first frame for tabletop object reconstruction.

Related Skills

Explore More Software Engineering Skills→
RayzerrekRayzerrek

unity-scene

Create, load, save, unload, and inspect Unity scenes in one workflow.

Community
Advanced
Geuan666Geuan666

robotwin-instruction-to-env

Transforms a user task name and description into a RoboTwin environment and renders the first deterministic frame to verify usability.

Community
Advanced
BBufBBuf
721

sglang-qwen-vlm-omni-asr-optimization

Optimize Qwen multimodal pipelines in SGLang using PR-diff-driven workflows and runtime references.

Community
Advanced
gesmith0606gesmith0606

notebooklm

Generate NFL rankings and podcast markdown from projection CSVs for NotebookLM.

Community
Intermediate