agentleFS
sandraschisandraschi/blender-mcp/skills/autonomous-modeling/SKILL.md

autonomous-modeling

Skill63 starsChanged 7 months agoMITView on GitHub

Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Discovery: Call blender_status() to assess current scene state.

    line 32
  2. Very specific:

    Planning: Use agentic_blender_workflow(workflow_prompt="...") to generate a high-level modeling plan with step breakdown.

    line 33
  3. Very specific:

    Execution: Create base geometry with create_cube() / create_cylinder(), refine with apply_modifier(), texture with set_material().

    line 34
  4. Very specific:

    Refinement: If the initial model is too simple, use intelligent_3d_processing(prompt="...") for detail pass — add edge loops, bevels, or …

    line 35
  5. Distinctive:

    Validation: Check for mesh integrity (non-manifold edges, zero-area faces, ngons) before finalization.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Autonomous Modeling Skill

Description: Expert Blender 3D modeler for autonomous procedural generation, parametric modeling, topology optimization, and script-based creation. Covers multi-step modeling workflows, procedural generation pipelines, and geometry node-based asset creation.

Trigger Phrases

  • "Model a [object] with [features]"
  • "Generate a procedural [part/asset]"
  • "Create a parametric [object] with adjustable parameters"
  • "Design a [style] [object] with detailed [elements]"
  • "Optimize topology on this mesh"
  • "Generate a low-poly version of [object]"
  • "Create a modular kit of [theme] parts"

Tools

  • agentic_blender_workflow(workflow_prompt="...") — Autonomous multi-step modeling via natural language. Plans and executes: create, modify, texture, validate.
  • intelligent_3d_processing(prompt="...", context="...") — Refine existing models: add modifiers, adjust materials, fix geometry issues.
  • blender_status() — Current scene state: object count, active object, render engine, viewport mode.
  • blender_list_tools() — Available Blender MCP capabilities and their parameters.
  • create_cube(), create_cylinder(), create_cone() — Add primitive mesh objects (one op per primitive).
  • apply_modifier(modifier_type="...", ...) — Apply modifiers (subdivision, mirror, boolean, bevel, solidify).
  • set_material(object_name="...", material="...", color=[...]) — Assign or create materials.

Workflow

  1. Discovery: Call blender_status() to assess current scene state. Use blender_list_tools() if unsure of available operations.
  2. Planning: Use agentic_blender_workflow(workflow_prompt="...") to generate a high-level modeling plan with step breakdown.
  3. Execution: Create base geometry with create_cube() / create_cylinder(), refine with apply_modifier(), texture with set_material().
  4. Refinement: If the initial model is too simple, use intelligent_3d_processing(prompt="...") for detail pass — add edge loops, bevels, or extruded details.
  5. Validation: Check for mesh integrity (non-manifold edges, zero-area faces, ngons) before finalization. Use Blender's 3D print toolbox if available.

Examples

Creating a Sci-Fi Robot

"I need a steampunk robot with exposed gears and copper plates." → agentic_blender_workflow(workflow_prompt="steampunk robot with gears and copper plates") → intelligent_3d_processing(prompt="Add gear details to joints and copper material finish")

Modular Environment Kit

"Create a modular sci-fi wall panel with indented vents, 4 units wide." → agentic_blender_workflow(workflow_prompt="modular scifi wall panel 4u with vents") → verify repeatability via array modifier

Parametric Object

"Generate a parametric gear with adjustable teeth count and radius." → create_cylinder() → apply_modifier("geometry_nodes", node_group="parametric_gear")

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.