agentleFS
SFKislevSFKislev/Flue/skills/blender/SKILL.md

Blender

Skill102 starsChanged 6 months agoMITView on GitHub

Control Blender from the shell via Flue - a Python bridge to bpy without an MCP server.

  • Installs packages

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

This skill lets a coding agent operate Blender on the desktop through Flue, a local shell-to-application bridge. The agent pipes Python into blender_bridge.py and gets structured JSON back. Flue is not an MCP server — it is a thinner, simpler shell contract that drives Blender's own bpy runtime directly.

agent shell -> blender_bridge.py -> bpy -> JSON result

When to use

The human requests work performed inside Blender — inspect the open scene, collections, objects, meshes, materials, selection; make bounded edits; run small bpy scripts. A CLI agent cannot act inside Blender without a bridge like Flue.

How to proceed

  1. Read FLUE.md in this directory first. It explains how Flue works, the bridge contract, a worked bpy example, and safety expectations.
  2. If Flue is installed: also read C:\Users\fredd\.claude\skills\flue\SKILL.md and adapters/blender_adapter/APP.md for the operational contract, then work from there.
  3. If Flue is not installed: tell the human. The install command is pip install flue && flue setup. Do not install without explicit approval in the current session.

Other apps

Flue also supports Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition, Houdini, 3ds Max, Unity, and Microsoft Office through the same stdin/stdout contract. One install covers all adapters.

Safety

Flue acts inside professional desktop software. Treat the human as the driver; prefer small, inspectable steps; avoid destructive actions unless explicitly requested. Flue is MIT-licensed and reviewable on GitHub / PyPI before use.

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.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.