Skip to content

MAX-786/claude-3d-harness / library/cc/text-to-blender

text-to-blender

Verified

Drive Blender from natural language. Converts plain-English requests ("model a sword and render it with cinematic lighting", "make this glass look frosted", "set up three-point lighting", "export this scene as glTF for the web") into Blender Python code executed via the Blender MCP server. Acts as the orchestrator that picks and chain-loads specialised sub-skills (blender-modeling, blender-materials, blender-lighting, blender-cameras, blender-rendering, blender-animation, blender-export, wireframe-to-3d, blender-pro-workflow, blender-skill-harmonizer, quality-refinement-autoloop). Use this skill whenever the user wants Claude to do anything in Blender, including creating geometry, applying materials, lighting a scene, framing a camera, rendering, animating, or exporting. Make sure to invoke this skill even if the user does not say "Blender" — also covers requests like "create a 3D model of...", "render this...", "make a glTF from...", "set up a scene with...", or any 3D-creation task. Requires the Blender MCP addon (ahujasid/blender-mcp) running on port 9876.

FileKindSize
SKILL.mdskill md18.0 KB
assets/v0.4.0-validation/README.mdmarkdown1.5 KB
assets/v0.4.0-validation/test1-modeling-materials-lighting-render.webpbinary7.2 KB
assets/v0.4.0-validation/test2-glass-cycles.webpbinary12.9 KB
assets/v0.4.0-validation/test3-anim-frame001.webpbinary3.0 KB
assets/v0.4.0-validation/test3-anim-frame048.webpbinary3.0 KB
assets/v0.4.0-validation/test3-anim-frame096.webpbinary3.0 KB
assets/v0.6.0-round2-validation/M_sword_FINAL_v0.6.0.webpbinary4.2 KB
assets/v0.6.0-round2-validation/M_sword_attempt1_broken_world.webpbinary4.8 KB
assets/v0.6.0-round2-validation/M_sword_attempt2_clean_world.webpbinary6.4 KB
assets/v0.6.0-round2-validation/M_sword_attempt3_aimed_lights.webpbinary8.1 KB
assets/v0.6.0-round2-validation/M_sword_attempt4_correct_dimensions_wrong_orientation.webpbinary3.2 KB
assets/v0.6.0-round2-validation/M_sword_attempt5_rotated_no_taper.webpbinary3.3 KB
assets/v0.6.0-round2-validation/M_sword_attempt6_with_pointed_tip.webpbinary3.7 KB
assets/v0.6.0-round2-validation/README.mdmarkdown2.8 KB
assets/v0.7.0-bottle-validation/README.mdmarkdown2.4 KB
assets/v0.7.0-bottle-validation/bottle_FINAL_v0.7.0.webpbinary8.7 KB
assets/v0.7.0-bottle-validation/bottle_first_try.webpbinary8.4 KB
assets/v0.8.0-chair-validation/README.mdmarkdown3.7 KB
assets/v0.8.0-chair-validation/chair_FINAL_v0.8.0.webpbinary16.6 KB
assets/v0.8.0-chair-validation/chair_attempt1_simple_rectangles.webpbinary18.5 KB
assets/v0.8.0-chair-validation/chair_attempt2_overcooked_wood.webpbinary26.0 KB
assets/v0.8.0-chair-validation/chair_attempt3_balanced_wood.webpbinary14.1 KB
assets/v0.9.0-validation/01_bottle_glass_class_lighting.webpbinary7.9 KB
assets/v0.9.0-validation/02_bottle_proper_wine_density.webpbinary8.5 KB
assets/v0.9.0-validation/03_aviator_wireframe_to_3d.webpbinary6.3 KB
assets/v0.9.0-validation/04_aviator_chained_upgrade.webpbinary13.4 KB
assets/v0.9.0-validation/05_aviator_proper_rayban_dimensions.webpbinary11.6 KB
assets/v1.1.0-validation/desk_lamp_emission.webpbinary7.9 KB
assets/v1.2.0-validation/01_broadcaster_too_bright.webpbinary9.2 KB
assets/v1.2.0-validation/02_broadcaster_neutral_dominates.webpbinary8.6 KB
assets/v1.2.0-validation/03_broadcaster_synthwave_FINAL.webpbinary10.9 KB
assets/v1.2.0-validation/04_broadcaster_with_features_still_not_human.webpbinary11.9 KB
references/assembly-order.mdmarkdown4.8 KB
references/blender-version-compat.mdmarkdown3.9 KB
references/common-object-dimensions.mdmarkdown12.0 KB

assets/v0.6.0-round2-validation/README.md

View on GitHub
# Round 2 Validation Renders — Sword Scene: Failure Modes → Final

Seven renders documenting the full investigation arc from "recipes verbatim" through every recipe gap surfaced and patched. Each iteration is the raw output Blender produced — none are cherry-picked.

## The investigation arc

| File | Recipe state | Outcome | What it revealed |
|------|-------------|---------|------------------|
| `M_sword_attempt1_broken_world.webp` | Recipes verbatim | Magenta floods scene | World tree leftover from earlier C2 HDRI test; Environment Texture had `image=None` |
| `M_sword_attempt2_clean_world.webp` | After manual world reset | Sword mostly in shadow | Lights at fixed coords with hardcoded rotations; no subject-aware aim |
| `M_sword_attempt3_aimed_lights.webp` | + aimed lights + reframed | Parts visible but blade clips top | Camera lacks bbox-aware framing |
| `M_sword_attempt4_correct_dimensions_wrong_orientation.webp` | + proper sword dimensions (78×4.5×0.8cm) | Looks like a "thin pole" | Camera viewing edge of blade (0.8cm thick), not broad face (4.5cm) |
| `M_sword_attempt5_rotated_no_taper.webp` | + Z-rotated 90° to face broad side | Visible blade but blunt tip | Top vertices scaled to 30%/50% leaves a chiseled flat |
| `M_sword_attempt6_with_pointed_tip.webp` | + merged top vertices to a point | Recognizable sword | Working — needed proper merge after collapse |
| **`M_sword_FINAL_v0.6.0.webp`** | All v0.6.0 patches applied; built fresh | Credible sword | Final result with all patches integrated |

## Six patches that came out of this

1. **`reset_world()` helper in orchestrator** — prevents broken Environment Texture state from corrupting renders
2. **`references/common-object-dimensions.md`** — real-world reference proportions (sword: 78×4.5×0.8cm blade, not "guess")
3. **`aim_at(light, target)` helper in `blender-lighting`** + Recipe 0 (subject-aware three-point)
4. **Bbox-aware camera framing** in `blender-cameras` Recipe 0 — fits subject to ~80% of vertical frame at the chosen focal length
5. **Axis-orientation guidance** in `blender-modeling` for elongated objects (broad face vs thin edge; rotate so broad axis faces camera)
6. **Proper tapering recipe** in `blender-modeling` — collapse top verts AND `remove_doubles` (without merge, the four collapsed verts stay distinct → degenerate "fake point")

## Meta-lesson committed to the orchestrator

The orchestrator's workflow now includes a **mandatory visual validation checkpoint** between rendering and reporting success. Numerical checks (object count, file size, no API errors) passed on every iteration above — but iterations 1, 2, 3, 4, 5 all looked broken. The user catching this is what drove the patches. The orchestrator must look at the picture before declaring done.

See `test_round2.md` at repo root for the full investigation, root causes, and patches.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall