Material Override logo

Material Override

OrganizationPopular
AgibotTech
material-override

Tune PBR metallic / roughness on URDF visual meshes without re-exporting DAE — author an inline `<material_override>` element inside any `<visual>`, and let the engine's URDF→USD pipeline patch the converter's defaults post-conversion. Useful for sim-to-real visual fidelity (DAE materials round-trip poorly; Isaac Sim's importer lands every embedded material at roughness=0.5, metallic=0.0 by default). Trigger: When the user asks to "tune material", "change roughness / metallic", "make the gripper shinier", "fix dull PBR", "override material", "PBR override", or any time the simulator looks washed out after a URDF→USD import.

Overview

PublisherAgibotTech
Repositorygenie_sim
Skill namematerial-override
Stars
1.4K
Forks
119
Bundled files
Instructions only
LicenseMPL-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AgibotTech on GitHub. Read the source before you install it.

Installation

Install the Material Override AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgibotTech/genie_sim.git /tmp/genie_sim
mkdir -p .claude/skills
cp -r /tmp/genie_sim/source/geniesim_ros/skills/material-override .claude/skills/material-override
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Material Override in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Material Override on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Material Override is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to Use

  • Robot or asset visual meshes import with washed-out / flat shading after the URDF→USD converter runs.
  • User wants to A/B PBR values without re-exporting DAE meshes from Blender / Maya.
  • Polishing a robot for sim-to-real visual transfer.
  • Author of a new URDF (see add-robot skill) wants the meshes to look right without round-tripping DAE materials.

Do not use for:

  • Replacing albedo / textures → must be done in the DAE export.
  • Per-prim material at runtime → that's a runtime USD edit, not the <material_override> element.
  • Adding a brand-new material — only patches metallic / roughness on the embedded one.

Critical Patterns

  1. Author inside <visual>, not on the link. The override auto-scopes to exactly the mesh it sits under. A link with N <visual> elements just gets N independent overrides.
  2. urdfdom / RSP / MoveIt / Isaac's converter all ignore it. assemble_robot.py strips the element from the URDF it feeds the converter, then re-applies the values to the converted USD via _parse_material_override_blocks / _apply_material_overrides.
  3. Only roughness and metallic are exposed. Other UsdPreviewSurface inputs (specular, opacity, IOR) are not on the contract.
  4. Range 0..1. Outside that range the importer warns and clamps.
  5. No attributes needed. Scoping is positional. Don't try to target a sibling visual by name — author one override per visual.

Schema

xml
<visual>
  <origin xyz="0 0 0" rpy="0 0 0"/>
  <geometry>
    <mesh filename="package://.../base_link.dae"/>
  </geometry>
  <material_override>
    <roughness>0.45</roughness>
    <metallic>0.85</metallic>
  </material_override>
</visual>

Either child is optional — author only what you need. Default for an absent child is "leave as the converter wrote it" (typically 0.5 / 0.0 for DAE imports).

PBR cheat-sheet

LookroughnessmetallicNotes
Brushed steel0.400.95Most arm shells
Anodised aluminium0.550.30UR-style structural
Polished chrome0.051.00Decorative trims, mirror parts
Matte plastic0.700.00Cable guards, end-stops
Rubber pads0.850.00Soft contact surfaces
Anodised gold (gripper bushings)0.300.90Highlights

These are starting points; A/B against a photograph of the real robot if you have one.

Workflow

Step 1 — Find the visual you want to tune

bash
# Locate the URDF / xacro under genie_sim_robot_model
grep -nR "<visual>" source/geniesim_ros/src/ros_ws/src/genie_sim_robot_model/robots/ | head

Step 2 — Add the override

Open the xacro, drop <material_override> into the <visual> block. Existing reference: aloha arm xacro carries an override on every visual:

xml
<visual>
  <origin xyz="0 0 0" rpy="0 0 0" />
  <geometry>
    <mesh filename="${mesh_dir}/base_link.dae" />
  </geometry>
  <material_override><roughness>0.45</roughness><metallic>0.85</metallic></material_override>
</visual>

Step 3 — Rebuild the workspace

bash
geniesim ros build dev && source devel/setup.bash

Step 4 — Force a USD regenerate

The robot USD is cache-gated by manifest.json. Bust the cache:

bash
rm -rf assets/scenes/<scene>/
# OR pass at launch:
ros2 launch genie_sim_bringup app.launch.py … always_regenerate_robot_usd:=true

Step 5 — Launch and inspect

bash
ros2 launch genie_sim_bringup app.launch.py \
  scene:=<scene> \
  launcher_config:=launcher_ovrtx_isaac_physx \
  headless:=false   # local workstation with a screen; flip to true on a remote/headless host

In the OVRtx viewport, compare against the unmodified baseline. Iterate values, rebuild, re-launch.

Step 6 — Verify the converted USD

bash
grep -n "roughness\|metallic" assets/scenes/<scene>/robot/robot.usda | head

You should see the patched values on the relevant material prims.

Notes

  • assemble_robot.py walks each <visual> in author order; if a visual has multiple meshes (rare in our robots), the override applies to every embedded material of that visual.
  • The override is stripped from the URDF before it reaches the converter, so MoveIt / RSP / urdfdom never see it. They'll happily consume the same xacro.
  • For brand-new materials (no DAE-embedded source), prefer authoring a real <material> block — material_override is patch-only.
  • Material is rendered by OVRtx + Isaac Sim. The Newton GL viewer uses simple shading and won't reflect roughness / metallic — use OVRtx for visual QA.

Resources

Frequently asked questions

What does the Material Override AI skill do?

Tune PBR metallic / roughness on URDF visual meshes without re-exporting DAE — author an inline `<material_override>` element inside any `<visual>`, and let the engine's URDF→USD pipeline patch the converter's defaults post-conversion. Useful for sim-to-real visual fidelity (DAE materials round-trip poorly; Isaac Sim's importer lands every embedded material at roughness=0.5, metallic=0.0 by default). Trigger: When the user asks to "tune material", "change roughness / metallic", "make the gripper shinier", "fix dull PBR", "override material", "PBR override", or any time the simulator looks w...

Why use Material Override on TypingMind?

Because you install it once and use it with any model. Material Override is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Material Override in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_ros/skills/material-override. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Material Override?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Material Override?

As many as you like. As long as a model supports skills, you can use Material Override with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Material Override AI skill free?

Yes. It is published on GitHub by AgibotTech under the MPL-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇