blender-skill-harmonizer
Skill2 starsChanged 3 days agoMITView on GitHub
Harmonize multiple Blender skills into a coherent pipeline with clear activation precedence, handoff artifacts, dependency gates, and conflict-resolution rules. Use when a Blender task spans several skills, when reference-locked work conflicts with generic production workflow, after adding/updating skills, or when repeated failures indicate skill interference or missing inter/intra-play.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- keysforthewin/thisofficeedited, first seen Jul 24, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- keysforthewin/thisoffice★ 098% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/3d-fabric.mdcCursor rule
- 3d-fabricSkill
- animation-quality-gateSkill
- atlas-uv-fittingSkill
- blender-animationSkill
- blender-camerasSkill
- blender-exportSkill
- blender-lightingSkill
- blender-materialsSkill
- blender-modelingSkill
- blender-pro-workflowSkill
- blender-renderingSkill
- blender-uv-texturingSkill
- closed-surface-uv-coverageSkill
- contour-to-meshSkill
- fit-repair-optimizerSkill
- landmark-fit-repairSkill
- mascot-logo-reconstructionSkill
- multiview-constraint-solverSkill
- multiview-fit-loopSkill
- orbital-hud-motionSkill
- orthographic-registrationSkill
- quality-refinement-autoloopSkill
- reference-analysis-validatorSkill
- reference-look-calibrationSkill
- reference-to-3dSkill
- source-part-segmentationSkill
- text-to-blenderSkill
- texture-driven-mesh-fittingSkill
- texture-state-animationSkill
- wireframe-to-3dSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use when: Multi-skill Blender orchestration, skill graph audits, resolving overlaps between …
- Distinctive: line 12
Before the first Blender call, read ../text-to-blender/references/mcp-backends.md.
- Distinctive: line 17
Use a Merge → Consistency → Optimize → Store cycle:
- Distinctive: line 22
Store: write the chosen plan and durable lessons into project docs/memory.
- Distinctive: line 59
Every non-trivial multi-skill pipeline should keep these files in the output folder:
- Distinctive: line 71
Source conflict beats implementation: If templates disagree, stop claiming final fit and write a conflict report.
- Distinctive: line 73
Reference-locked geometry beats generic modeling: Do not primitive-first rebuild after a contour/source mask exists.
- Distinctive: line 75
Lighting/look waits for material and camera lock: Do not tune lights to compensate for wrong geometry.
- Distinctive: line 76
Export waits for validation: No final GLB without pass/fail reports.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCP backend
Use when: Multi-skill Blender orchestration, skill graph audits, resolving overlaps between text-to-blender/pro-workflow/reference-to-3d/wireframe/UV/fit/repair skills, defining source-of-truth precedence, artifact contracts, and sequential-vs-parallel execution plans.
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 Skill Harmonizer
This is the meta-layer for the Blender skill stack. It prevents independently useful skills from producing incoherent work when combined.
Use a Merge → Consistency → Optimize → Store cycle:
- Merge: list all triggered skills and their intended outputs.
- Consistency: detect conflicts in assumptions, coordinate systems, source hierarchy, object naming, or validation gates.
- Optimize: choose one orchestrator, one source-of-truth policy, and a staged/parallel execution plan.
- Store: write the chosen plan and durable lessons into project docs/memory.
Skill category map
- Top-level orchestrators:
text-to-blender,quality-refinement-autoloop,mascot-logo-reconstruction. - General production:
blender-pro-workflow,blender-modeling,blender-materials,blender-lighting,blender-cameras,blender-rendering,blender-animation,blender-export. - Reference reconstruction:
reference-to-3d,wireframe-to-3d,reference-analysis-validator,source-part-segmentation,orthographic-registration,multiview-constraint-solver,contour-to-mesh,texture-driven-mesh-fitting,landmark-fit-repair,multiview-fit-loop,fit-repair-optimizer. - Texture/UV:
blender-uv-texturing,atlas-uv-fitting,closed-surface-uv-coverage. - Look calibration:
reference-look-calibration. - Animation/motion design:
texture-state-animation,orbital-hud-motion,animation-quality-gate, coordinated byblender-animation. - Task-specific/full workflow:
mascot-logo-reconstruction.
Activation precedence
For a task involving references/templates/textures:
blender-skill-harmonizer— choose the pipeline and conflict policy. 1a.quality-refinement-autoloop— if output is rejected/subpar, freeze product work, diagnose, sanitize/patch generic skill knowledge, validate, then retry.reference-analysis-validator— source manifest and source-of-truth classification.orthographic-registration— view consistency and coordinate contract.multiview-constraint-solver— rigid feasibility and canonical view policy.fit-repair-optimizer— dependency repair queue if validation fails.source-part-segmentation— split overlapping structural/decorative masks.contour-to-mesh/wireframe-to-3d/blender-modeling— geometry, selected by source type.texture-driven-mesh-fitting+landmark-fit-repair— fit mesh boundaries and named landmarks to source/texture.atlas-uv-fitting/blender-uv-texturing/closed-surface-uv-coverage— UV, texture fit, and full front/back/side surface coverage.multiview-fit-loop— render/compare/adjust loop.reference-look-calibration+blender-materials/blender-lighting/blender-rendering— look only after geometry/UV gates.blender-export— only after validation gates.blender-animation— only after static fit acceptance.texture-state-animation/orbital-hud-motion— design texture/HUD motion as layered, source-derived animation.animation-quality-gate— render contact sheet and reject bad motion before final export.
Generic blender-pro-workflow is subordinate to the reference-locked order whenever the source is a template/brand asset.
Shared artifact contract
Every non-trivial multi-skill pipeline should keep these files in the output folder:
reference_manifest.jsonregistration_report.jsonatlas_regions.jsonvalidation/multiview_fit_report.jsonvalidation/*_overlay.pngALIGNMENT_REPAIR_QUEUE.jsonor equivalent when gates failBUILD_NOTES.md
Conflict rules
- Source conflict beats implementation. If templates disagree, stop claiming final fit and write a conflict report.
- Front-view brand read beats side/back/top unless canonical policy says otherwise.
- Reference-locked geometry beats generic modeling. Do not primitive-first rebuild after a contour/source mask exists.
- UV/texture fit waits for geometry lock. Texture audit may run in parallel, but final UV assignment waits.
- Lighting/look waits for material and camera lock. Do not tune lights to compensate for wrong geometry.
- Export waits for validation. No final GLB without pass/fail reports.
Sequential vs parallel orchestration
Sequential gates:
- source conflict / multiview rigidity
- structural part count
- front geometry
- multiview geometry
- UV/material texture fit
- lighting/look
- export/animation
Parallel lanes allowed after their blockers clear:
- atlas region classification can run while geometry is being repaired;
- lighting reference statistics can run while UVs are being prepared;
- export target checks can run while visual validation is pending;
- validation tooling improvements can run anytime, but must not mutate product geometry.
Read when needed
references/handoff-contracts.mdfor exact input/output contracts between skills.
Script
scripts/skill_graph_audit.pyaudits the local manifest, roles, missing paths, and overlap warnings.
Animation handoff rule
For reference-locked mascots/logos, animation is not a generic spin/pulse task. Use texture-state-animation for material/texture state changes, orbital-hud-motion for circles/HUD/aura, and animation-quality-gate before accepting or exporting. If an animation is rejected as ugly, run a RALPH loop before rebuilding.
Closed-surface coverage handoff rule
For closed or extruded reference-locked assets, front texture fit is not enough. Before look-dev or animation acceptance, run closed-surface-uv-coverage to verify that front cap, back cap, and sidewall surfaces each have explicit UV/generated/procedural coverage. Curves, planes, HUD, and aura elements are accents only and do not count as surface texture fill.
Quality-refinement autoloop handoff rule
When a user rejects output quality, or repeated failures show missing skill depth, do not continue blind retries. Invoke quality-refinement-autoloop: preserve the baseline, capture evidence, classify failure dimension, decide whether existing skills are sufficient, sanitize any new lesson into generic skill guidance, validate the skill stack, then repair the artifact. Publication prep is only done on explicit user request.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

