Blender Uv Texturing logo

Blender Uv Texturing

Community
RobLe3
blender-uv-texturing

UV unwrap, atlas-map, project textures, use alpha decals, bake maps/lightmaps, and prepare texture-driven Blender assets for glTF/GLB export. Use whenever the user provides texture packs, texture atlases, decals, UV layouts, lightmaps, wants a texture to fit a mesh 1:1, or reports stretched/off textures. Pairs with reference-to-3d for template-accurate reconstruction and blender-materials for PBR values.

Overview

PublisherRobLe3
Repositorycc-blender-skill
Skill nameblender-uv-texturing
Stars
131
Forks
14
Bundled files
2
LicenseMIT
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by RobLe3 on GitHub. Read the source before you install it.

Installation

Install the Blender Uv Texturing 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.
    https://github.com/RobLe3/cc-blender-skill/tree/main/plugin/skills/blender-uv-texturing
  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/RobLe3/cc-blender-skill.git /tmp/cc-blender-skill
mkdir -p .claude/skills
cp -r /tmp/cc-blender-skill/plugin/skills/blender-uv-texturing .claude/skills/blender-uv-texturing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blender Uv Texturing 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 Blender Uv Texturing 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 Blender Uv Texturing 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.

MCP backend

Use when: Texture atlas/UV/baking/lightmap/decal work in Blender; any request involving texture fit, UV islands, project-from-view, texture packs, alpha decals, or baked maps.

Before the first Blender call, read ../text-to-blender/references/mcp-backends.md. Prefer official MCP for shared capabilities; preserve the selected backend for the whole task. Tool names in recipes are client/legacy examples: map them through that reference and its agent-host guide.

Blender UV Texturing

This skill fills the gap between “assign a material” and “the supplied texture pack actually fits the model.” It is mandatory for template/atlas-driven assets.

Decision tree

What does the texture represent?
├── Whole object from front/reference → Project-from-View style UVs from the validation camera
├── Atlas with separate parts         → crop/map each part to its own UV island/rectangle
├── Repeating material                → generated/object coords or tiled UVs
├── Face/expression decal             → alpha material plane or projected UV island; no black background
├── Roughness/bump/normal map         → Non-Color data, correct node type
└── Lightmap                          → separate UV/lightmap channel or optional multiply helper; not emission

Non-negotiable rules

  1. Image textures need a material node setup to render/export; viewport UV display alone is not enough.
  2. Basecolor/albedo = sRGB. Roughness, metallic, bump, normal, AO/lightmap = Non-Color.
  3. Atlas textures must be mapped by region. Never apply a full atlas to every mesh part.
  4. Alpha decals must use alpha-connected material settings (BLEND, Alpha Hashed, or Alpha Clip) and a keyed/correct PNG. Do not leave black planes.
  5. For GLB, keep to exporter-recognized nodes where possible: Principled BSDF with Image Texture inputs, UVs, normals, tangents.
  6. Validate with a checker texture or overlay render before final material tuning.

Recipes

Create front-projected UVs from world X/Z bounds

python
import bpy

def assign_front_projected_uv(obj_name, uv_name='UV_front_projected'):
    obj = bpy.data.objects[obj_name]
    mesh = obj.data
    uv = mesh.uv_layers.get(uv_name) or mesh.uv_layers.new(name=uv_name)
    mesh.uv_layers.active = uv
    xs = [v.co.x for v in mesh.vertices]
    zs = [v.co.z for v in mesh.vertices]
    minx, maxx = min(xs), max(xs)
    minz, maxz = min(zs), max(zs)
    dx = max(maxx - minx, 1e-8)
    dz = max(maxz - minz, 1e-8)
    for poly in mesh.polygons:
        for li in poly.loop_indices:
            co = mesh.vertices[mesh.loops[li].vertex_index].co
            uv.data[li].uv = ((co.x - minx) / dx, (co.z - minz) / dz)
    mesh.update()

Map a mesh to a rectangle in an atlas

Atlas rectangle is [u0, v0, u1, v1] in normalized UV coordinates. Use this after creating local 0–1 UVs.

python
def remap_uv_rect(obj_name, rect, uv_name=None):
    obj = bpy.data.objects[obj_name]
    layer = obj.data.uv_layers.get(uv_name) if uv_name else obj.data.uv_layers.active
    u0, v0, u1, v1 = rect
    for item in layer.data:
        u, v = item.uv
        item.uv = (u0 + u * (u1-u0), v0 + v * (v1-v0))
    obj.data.update()

Image texture material with correct color spaces

python
import bpy

def image(path, colorspace):
    img = bpy.data.images.load(path, check_existing=True)
    img.colorspace_settings.name = colorspace
    return img

def make_pbr_texture_material(name, basecolor, roughness=None, normal_or_bump=None, alpha=False):
    mat = bpy.data.materials.new(name)
    mat.use_nodes = True
    nt = mat.node_tree
    bsdf = nt.nodes.get('Principled BSDF')
    tex = nt.nodes.new('ShaderNodeTexImage')
    tex.image = image(basecolor, 'sRGB')
    nt.links.new(tex.outputs['Color'], bsdf.inputs['Base Color'])
    if alpha and 'Alpha' in bsdf.inputs:
        nt.links.new(tex.outputs['Alpha'], bsdf.inputs['Alpha'])
        mat.blend_method = 'BLEND'
    if roughness:
        r = nt.nodes.new('ShaderNodeTexImage')
        r.image = image(roughness, 'Non-Color')
        nt.links.new(r.outputs['Color'], bsdf.inputs['Roughness'])
    if normal_or_bump:
        btex = nt.nodes.new('ShaderNodeTexImage')
        btex.image = image(normal_or_bump, 'Non-Color')
        bump = nt.nodes.new('ShaderNodeBump')
        bump.inputs['Strength'].default_value = 0.02
        nt.links.new(btex.outputs['Color'], bump.inputs['Height'])
        nt.links.new(bump.outputs['Normal'], bsdf.inputs['Normal'])
    return mat

Bake target setup

Blender baking requires a UV map and an active Image Texture node or color attribute as the bake target. Use Cycles for baking.

python
import bpy

obj = bpy.data.objects['GEO-target']
bpy.context.scene.render.engine = 'CYCLES'
img = bpy.data.images.new('BAKE_target', 2048, 2048, alpha=True)
mat = obj.data.materials[0]
mat.use_nodes = True
node = mat.node_tree.nodes.new('ShaderNodeTexImage')
node.image = img
mat.node_tree.nodes.active = node
bpy.context.view_layer.objects.active = obj
obj.select_set(True)
bpy.ops.object.bake(type='DIFFUSE', pass_filter={'COLOR'}, margin=16)
img.filepath_raw = '/tmp/bake_target.png'
img.file_format = 'PNG'
img.save()

Closed/extruded surface coverage gate

For closed or extruded assets, do not stop at front projection. Use closed-surface-uv-coverage to verify front cap, back cap, and sidewall material/UV/generated coverage separately. Back/side curve overlays are accents, not texture fill.

Validation checklist

  • UV layer exists and is active.
  • Checker texture shows no obvious stretching on front-facing parts.
  • Atlas rectangles are per-part, not whole-atlas everywhere.
  • Roughness/bump/normal/lightmap color spaces are Non-Color.
  • Alpha material has blend mode set and no black backing plane.
  • Base GLB embeds/exports expected images and excludes reference planes.
  • A front overlay render confirms the texture aligns with the source template.

Sources distilled

  • Blender Manual: UV/Image texture workflow requires material nodes for rendered texture output.
  • Blender Manual: Image Texture node uses active UV map when Vector is unconnected.
  • Blender Manual: Cycles baking requires a UV map and active Image Texture/Color Attribute target.
  • Blender Manual: glTF exporter supports meshes, UVs, textures, and materials based mainly on Principled BSDF.
  • Khronos glTF PBR: base color, metallic/roughness, normals and related maps are core concepts for realtime transfer.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Blender Uv Texturing AI skill do?

UV unwrap, atlas-map, project textures, use alpha decals, bake maps/lightmaps, and prepare texture-driven Blender assets for glTF/GLB export. Use whenever the user provides texture packs, texture atlases, decals, UV layouts, lightmaps, wants a texture to fit a mesh 1:1, or reports stretched/off textures. Pairs with reference-to-3d for template-accurate reconstruction and blender-materials for PBR values.

Why use Blender Uv Texturing on TypingMind?

Because you install it once and use it with any model. Blender Uv Texturing 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 Blender Uv Texturing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RobLe3/cc-blender-skill/tree/main/plugin/skills/blender-uv-texturing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Blender Uv Texturing?

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 Blender Uv Texturing?

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

Is the Blender Uv Texturing AI skill free?

Yes. It is published on GitHub by RobLe3 under the MIT 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 👇