MAX-786/claude-3d-harness / library/cc/reference-to-3d
reference-to-3d
VerifiedReconstruct 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.2 KB |
| references/overview.md | markdown | 1.3 KB |
| scripts/silhouette_validator.py | script | 2.3 KB |
| scripts/template_analyzer.py | script | 4.5 KB |
references/overview.md
View on GitHub# Reference-to-3D Domain Overview
## Why this exists
General Blender recipe skills generate plausible models. Brand/template reconstruction requires a stricter pipeline: **measure the source, build to measurements, validate with overlays**.
## Required capabilities
1. Source inventory and source-of-truth ranking.
2. CV extraction of contours, components, centroids, bboxes, symmetry pairs.
3. Semantic part inventory (structural vs decorative).
4. Front-locked silhouette mesh generation.
5. Multi-view registration: front X/Z, side Y/Z, top X/Y, back validation.
6. UV/atlas mapping and texture color-space handling.
7. Quantitative validation: part count, IoU, centroid distance, bbox error, SSIM.
8. Export gating: refuse if validation fails.
## Practical thresholds
- Front silhouette IoU: ≥ 0.90 for blockout, ≥ 0.95 for final logo/mascot.
- Part count: exact for named/visible structural parts.
- Centroid drift: ≤ 1% of image diagonal for facial features/brand marks.
- BBox scale error: ≤ 2–3% for primary silhouette.
## Implementation roadmap
- `template_analyzer.py`: produce component JSON from source art.
- `silhouette_validator.py`: compare reference/render masks.
- Blender builder helpers: make reference planes, front-projected UVs, contour-filled meshes.
- Validation render recipe: orthographic masks with solid unlit material.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |