Skills
.Work. You
Rest

qwen35-4b-nf4

Community

Instantly answer scene questions from RGB images and videos.

#multimodal#robotics#scene understanding#scene query#video language model
Authorbensonlee5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill allows you to query and understand scenes captured by RGB cameras, providing detailed textual descriptions and answering specific questions about the scene.

Core Features & Use Cases

  • Scene Query: Ask about objects, spatial relations, and task progress in a scene.
  • Video Support: Process and understand video sequences, extracting insights over time.
  • Embodiment-Agnostic: Works with any robot or embodiment with an RGB camera.
  • Use Case: Use this Skill to determine if a robot's task is complete by asking if it has grasped an object or if a task is progressing as expected.

Quick Start

Install the skill and query the scene: ral skill install hf://OpenRAL/rskill-qwen35-4b-nf4 and then query_scene -q "Has the robot grasped the mug?"

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: qwen35-4b-nf4
Download link: https://github.com/bensonlee5/openral/archive/main.zip#qwen35-4b-nf4

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.