reference-to-3d

Q: How do I install reference-to-3d?

Run npx skills add https://github.com/roble3/cc-blender-skill --skill reference-to-3d in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/reference-to-3d/ (personal) or .claude/skills/reference-to-3d/ (project).

by roble3Media & Creative

Reconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic front/side/back/top views, or mascot/logo art where visual fidelity to the source is more important than a plausible generated object. Use when the user says the model must match a template, wireframe, texture pack, character sheet, mascot sheet, or brand asset exactly; also use after feedback like "does not look like the reference", "fit the texture 1:1", "wrong number of visible parts", or "compare against the template". Requires Blender MCP plus local Python with Pillow/OpenCV/numpy; pairs with blender-uv-texturing, wireframe-to-3d, blender-modeling, blender-materials, and blender-export.

Installs: 1.3K
Last 24h: +41
Trending rank: #3837
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/roble3/cc-blender-skill --skill reference-to-3d

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads reference-to-3d automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

MCP backend

Use when: User supplies reference images/templates/texture atlases/orthographic views and wants a model matching them, or repeated visual mismatch feedback requires a reference-locked corrective loop.

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.

Reference-to-3D Reconstruction

This skill is for source-locked modeling: the reference asset is the contract. Do not generate a plausible object from memory and then decorate it. Extract measurements, part counts, silhouettes, and UV regions from the supplied files first, then build the Blender model to satisfy those measurements.

1:1 reconstruction upgrade

When the user requires true 1:1 matching, chain these skills instead of attempting another plausible modeling pass:

reference-analysis-validator for manifest, masks, part counts, overlay gates.
orthographic-registration for front/side/back/top coordinate agreement.
contour-to-mesh for silhouette-derived structural meshes.
atlas-uv-fitting for per-part texture/UV fitting.
mascot-logo-reconstruction as the full orchestrator for brand mascot/logo work.

Do not export a final asset until the validation JSON and overlay render pass the manifest thresholds.

Triggered failure mode

If the user says the output does not match the templates/textures/wireframes, stop regular text-to-blender generation and enter this workflow. Repeated plausible-but-wrong renders usually mean the missing step is reference analysis, not another modeling iteration.

Source-of-truth hierarchy

Front template / front wireframe: primary silhouette, visible part count, face/feature positions, brand read.
Texture atlas: exact part shapes, color/material boundaries, decals, lightmap/aura intent.
Side/back/top views: depth, stacking order, thickness, backside forms. They must not change the locked front projection.
User feedback: hard constraints; promote it into validation gates.

Mandatory preflight checklist

Before Blender modeling, write a small reference_manifest.json with:

{
  "source_files": [],
  "primary_view": "front",
  "expected_primary_parts": {"count": null, "labels": []},
  "structural_parts": [],
  "decorative_parts": [],
  "texture_regions": [],
  "validation_thresholds": {
    "front_mask_iou_min": 0.90,
    "bbox_center_tolerance_px": 12,
    "part_count_exact": true
  }
}

If the expected part count is unclear, derive it from the reference sheet with the analyzer and show the user the uncertainty instead of guessing.

Pipeline

1. Inventory and classify sources

Classify each provided asset:

front_template: hero brand image or front wireframe.
side_view, back_view, top_view: orthographic depth references.
texture_atlas: basecolor / albedo atlas containing pieces.
decal: transparent face/expression or detail layer.
emissive, roughness, bump, normal, lightmap: material maps.
aura/background: optional visual context, not structural body geometry.

2. Analyze images locally

Use scripts/template_analyzer.py for first-pass component extraction:

python3 ${CLAUDE_SKILL_DIR}/scripts/template_analyzer.py   --image /path/to/front_reference.png   --out /tmp/front_analysis.json   --mode edges  # use bright_on_dark/dark_on_bright/alpha when cleaner

The analyzer returns components with area, perimeter-derived score, bbox, centroid, contour, and approximate class hints. Use --mode edges for faint grey wireframes and Otsu modes for clean masks/atlases. Treat this as measurement input, not final authority.

3. Lock the front reference in Blender

Create a front reference plane or Image Empty in the same orthographic camera used for validation. Prefix it REF_ and exclude it from export. Official Blender docs describe Image Empties as reference images/blueprints and support front/back depth, opacity, orthographic-only display, and axis-aligned display.

4. Build geometry from source contours

For each structural part:

Convert the 2D contour to front-view X/Z coordinates.
Generate a quad strip/grid inside that contour.
Assign Project-from-View-style UVs based on front X/Z bounds or exact atlas region.
Add only shallow Y-depth/crown/extrusion after the front silhouette is locked.
Keep part names semantic: GEO-subject_part_top, GEO-subject_face_shell, etc.

Do not radial-duplicate a mascot unless the reference is truly radial. Logos often have occlusion, intentional asymmetry, and a fixed visible part count.

5. Multi-view registration

Front X/Z is locked first.
Side view controls Y/Z depth envelope only.
Top view controls X/Y spread only.
Back view controls hidden/backside geometry and validation, not front silhouette.

If views disagree, keep the front brand read and document the conflict.

6. UV and texture mapping

Chain-load blender-uv-texturing when any texture pack is provided. For atlas-driven parts:

crop or map per atlas region; do not project the whole atlas onto every part;
front-facing hero surfaces use front-projected UVs;
side/back surfaces use side/back UV islands, procedural fill, or baked colors;
alpha decals need transparent material settings and must not introduce black planes;
lightmaps are optional realtime helpers and should not be connected as emission unless specified.

7. Validation gates before export

Always produce:

front_preview.png
front_overlay_reference.png
front_mask_validation.json
side_preview.png
back_preview.png
top_preview.png

Use scripts/silhouette_validator.py:

python3 ${CLAUDE_SKILL_DIR}/scripts/silhouette_validator.py   --reference /tmp/reference_mask.png   --render /tmp/render_mask.png   --out /tmp/validation.json

Refuse final export if:

primary part count differs from manifest;
front-mask IoU is below threshold;
face/feature centroid is outside tolerance;
optional aura/decorations are included in the base GLB by mistake.

Blender code patterns

Reference plane in front-view X/Z

import bpy

def create_reference_plane(name, image_path, width, height, y=0.2, alpha=0.35):
    img = bpy.data.images.load(image_path, check_existing=True)
    mat = bpy.data.materials.new('MAT-' + name)
    mat.use_nodes = True
    nodes = mat.node_tree.nodes
    bsdf = nodes.get('Principled BSDF')
    tex = nodes.new('ShaderNodeTexImage')
    tex.image = img
    mat.node_tree.links.new(tex.outputs['Color'], bsdf.inputs['Base Color'])
    mat.node_tree.links.new(tex.outputs['Alpha'], bsdf.inputs['Alpha'])
    bsdf.inputs['Alpha'].default_value = alpha
    mat.blend_method = 'BLEND'
    verts = [(-width/2,y,-height/2),(width/2,y,-height/2),(width/2,y,height/2),(-width/2,y,height/2)]
    mesh = bpy.data.meshes.new(name + 'Mesh')
    mesh.from_pydata(verts, [], [(0,1,2,3)])
    mesh.update()
    uv = mesh.uv_layers.new(name='UV')
    for li, uvco in zip(mesh.polygons[0].loop_indices, [(0,0),(1,0),(1,1),(0,1)]):
        uv.data[li].uv = uvco
    obj = bpy.data.objects.new('REF-' + name, mesh)
    bpy.context.collection.objects.link(obj)
    obj.data.materials.append(mat)
    obj.hide_render = True
    return obj

Validation print contract

print('VALIDATE expected_primary_parts=', expected, 'actual=', actual)
print('VALIDATE front_locked=True reference_overlay_rendered=True')
if actual != expected:
    raise RuntimeError('Part-count mismatch; refusing export')

When to stop and ask for human input

Ask for a correction only after generating evidence, e.g. an overlay image or JSON showing ambiguity. Do not ask vaguely. Example: “The analyzer finds N prominent structural components plus M faint background/decorative shapes. Should the GLB include only the structural components?”

Sources distilled

Blender Manual: Image Empties for reference images/blueprints; front/back display, opacity, orthographic and axis-aligned controls.
Blender Manual: Trace Image to Grease Pencil works best from manually prepared black/white images and controlled resolution.
Blender Manual: Shrinkwrap moves vertices to a target surface and is useful after silhouette lock for conforming secondary details.
Blender Manual: UV/Image Texture and Project-from-View-style workflows require UV maps and material nodes for renders/exports.
OpenCV docs: contour moments, area, perimeter, bounding boxes, template matching.
scikit-image docs: SSIM for image similarity when pixel-MSE is not perceptually meaningful.

FAQ

What does the reference-to-3d skill do?

How do I install reference-to-3d?

Run npx skills add https://github.com/roble3/cc-blender-skill --skill reference-to-3d in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/reference-to-3d/ (personal) or .claude/skills/reference-to-3d/ (project).

Which AI agents can use reference-to-3d?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is reference-to-3d safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains reference-to-3d?

It is published by roble3 in roble3/cc-blender-skill. It has 1,295 recorded installs.

More from roble3/cc-blender-skill

View all →

blender-modeling

roble3/cc-blender-skill

Create and edit 3D meshes in Blender — primitives, hard-surface modeling, mesh operators, modifier stacks (Bevel, Subdivision, Boolean, Mirror, Array, Solidify), bmesh-level edits, retopology basics. Use whenever the user asks to "make/model/create/build a 3D object", "shape/sculpt this", "add a cube/sphere/cylinder/etc.", "extrude/inset/bevel this face", "add a modifier", or any geometry-creation request that isn't a wireframe trace. Make sure to use this skill even if the user does not say "model" — also covers "make a sword", "build a chair", "add a door", "carve out a hole". Pairs with blender-materials for look-dev and blender-pro-workflow for full pipelines.

Media & Creative2.3K installs

blender-materials

roble3/cc-blender-skill

Create and assign PBR materials in Blender via Principled BSDF — metals, glass, plastic, fabric, skin, organics. Covers physically-based material recipes with real-world values, Coat layer (varnish/car paint), Sheen (cloth), Subsurface scattering (skin/wax), Transmission (glass), and procedural patterns (wood grain, marble, fabric weave). Use whenever the user asks to "make it look like X material", "give it a metallic finish", "apply a wood texture", "make this glass / plastic / brushed steel / leather / skin", or any look-development request. Make sure to use this skill even if the user does not say "material" — also covers "make it shiny", "matte finish", "looks like copper", "rough surface". Works with any geometry; pairs with blender-lighting (materials only look right under proper lighting).

1.7K installs

blender-export

roble3/cc-blender-skill

Export Blender scenes to glTF/GLB (web/AR), FBX (game engines), OBJ (universal), USD (VFX pipelines), STL (3D printing). Includes Unreal collision hulls and Multires normal-map baking for low-poly export, per-format settings, embed/unpack textures, axis conversion, polygon optimization (Decimate), and target-platform validation. Use whenever the user asks to "export this", "save as glTF / FBX / OBJ / STL / USD", "package for Unity / Unreal / Three.js / web / AR / 3D print", or any output format conversion. Make sure to use this skill even if the user does not say "export" — also covers "package this for the web", "make it work in Unity", "send to Unreal", "save for 3D printing".

Media & Creative1.4K installs

blender-rendering

roble3/cc-blender-skill

Render Blender scenes with the right engine and settings — Cycles for photoreal, EEVEE for speed/stylized, sample counts, denoising (OptiX/OIDN), light path tuning, color management (AgX/Filmic), file output (PNG/EXR/MP4), animation rendering. Use whenever the user asks to "render this", "produce an image", "render a frame / animation", "make a final image", "save the render", or any output-generation request. Make sure to use this skill even if the user does not say "render" — also covers "make a picture", "save the result", "produce a final image", "export as image".

Media & Creative1.4K installs

blender-animation

roble3/cc-blender-skill

Animate objects, cameras, lights, and properties in Blender — keyframes, F-curves, easing (Bezier, Linear, Sine, Bounce, Elastic), shape keys (morph targets / blendshapes / visemes), drivers (Python expressions on properties), NLA actions for reuse and layering. Use whenever the user asks to "animate this", "make it move / rotate / scale over time", "add keyframes", "loop / oscillate", "shape key / morph / blendshape", "visemes for lip sync", or any time-based property change. Make sure to use this skill even if the user does not say "animate" — also covers "spin it slowly", "make it wave", "fade in / out", "pulse", "facial expression".

Frontend & Design1.3K installs

blender-pro-workflow

roble3/cc-blender-skill

End-to-end production workflow guidance for Blender — the order to assemble scenes (block-out → camera → light → forms → materials → detail → render → composite → export), critique protocols, time budgets, and recovery patterns. Use whenever the user asks to "make a complete scene / hero shot / production-quality render", "what's the right order to do this", "set up a full pipeline", or has a multi-step request crossing modeling + lighting + materials + rendering. Make sure to use this skill for any request that spans multiple phases of 3D work, even if the user does not say "workflow" — also covers "make a final image of X", "produce a hero render", "professional-looking result".

Productivity & Automation1.3K installs

Popular media & creative skills

View category →

hyperframes

heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Media & Creative1.2M installs

media-use

heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Media & Creative1.1M installs

hyperframes-registry

heygen-com/hyperframes

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Media & Creative1M installs

hyperframes-creative

heygen-com/hyperframes

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.

Media & Creative916.5K installs

ai-video-generation

101-skills/superpowers

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Media & Creative881.5K installs

ai-image-generation

101-skills/superpowers

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Media & Creative880.3K installs

reference-to-3d

Install

Install

Describe the task

Review the result

SKILL.md

MCP backend

Reference-to-3D Reconstruction

1:1 reconstruction upgrade

Triggered failure mode

Source-of-truth hierarchy

Mandatory preflight checklist

Pipeline

1. Inventory and classify sources

2. Analyze images locally

3. Lock the front reference in Blender

4. Build geometry from source contours

5. Multi-view registration

6. UV and texture mapping

7. Validation gates before export

Blender code patterns

Reference plane in front-view X/Z

Validation print contract

When to stop and ask for human input

Sources distilled

FAQ

More from roble3/cc-blender-skill

Popular media & creative skills