agentsclimarketplace

Blender agent studio

Skill ifBars/blender-agent-studio

Codex plugin for reproducible Blender modeling, validation, animation, MCP tooling, and agent benchmarking

Install
npx -y skills add ifBars/blender-agent-studio

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Route Blender asset creation, refinement, procedural systems, rendering, simulations, characters, validation, animation, MCP integration, and agent benchmarking work to the appropriate Blender Agent Studio workflow. Use when an agent needs an end-to-end Blender workflow or when the correct specialist skill is not yet known.

SKILL.md

3.4 KB, as published. Nobody here has run it

Blender Agent Studio

Select the smallest set of specialist workflows that covers the request, then follow each selected SKILL.md completely.

Route the request

  • Build or substantially refine geometry: read plugins/blender-agent-studio/skills/blender-modeling-workflow/SKILL.md.
  • Clarify art direction or offer a concept/mockup reference before creation: read plugins/blender-agent-studio/skills/blender-art-direction-intake/SKILL.md.
  • Inspect an authored scene or exported asset: read plugins/blender-agent-studio/skills/blender-asset-validation/SKILL.md.
  • Create or diagnose articulated motion: also read plugins/blender-agent-studio/skills/blender-animation-workflow/SKILL.md.
  • Create Geometry Nodes, scattering, terrain, or parametric systems: read plugins/blender-agent-studio/skills/blender-procedural-workflow/SKILL.md.
  • Light, compose, render, or deliver stills, turntables, or sequences: read plugins/blender-agent-studio/skills/blender-rendering-workflow/SKILL.md.
  • Build, bake, or diagnose fluids, smoke, fire, cloth, rigid bodies, particles, hair, or soft bodies: read plugins/blender-agent-studio/skills/blender-simulation-workflow/SKILL.md.
  • Create, rig, skin, or export a character, avatar, or creature: read plugins/blender-agent-studio/skills/blender-character-workflow/SKILL.md.
  • Compare baseline, skill, prompt, or MCP capability: read plugins/blender-agent-studio/skills/blender-agent-benchmark/SKILL.md.
  • Choose, configure, or evaluate Blender MCP transport: read plugins/blender-agent-studio/skills/blender-mcp-integration/SKILL.md.

Use modeling plus validation for normal asset-generation requests. Add procedural, rendering, simulation, character, or animation workflows only when their respective capability is required.

Preserve the workflow contract

  1. Resolve and record the exact Blender executable and version.
  2. Convert the request into explicit parts, relationships, style, scale, animation, finish quality, export, evidence, and approval requirements.
  3. Unless the user explicitly requests low-poly, blockout-only, or another constrained style, target a polished smooth asset with intentional secondary and tertiary detail rather than a primitive-looking low-density result.
  4. Work through named stages: contract and references, graybox, primary and secondary forms, structural refinement, materials and textures, final surface polish, and export validation.
  5. Keep deterministic Python as the durable source for generated assets.
  6. Inspect both the authored scene and a fresh import of the exported artifact.
  7. Open and review fixed multiview evidence before claiming visual quality.
  8. Treat automated metrics as gates and measurements, not substitutes for request compliance or visual judgment.
  9. Keep benchmark conditions isolated and report failures, timing, and limitations alongside improvements.

Prefer the bundled bounded inspection and evidence tools when installed as a Codex plugin. Do not add generic arbitrary-Python MCP execution.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.