Export Pipeline logo

Export Pipeline

Community
arjun988
export-pipeline

Production export from Blender to FBX, GLTF, OBJ, USD, and Alembic with scale, pivot, rotation, normals, materials, animation, and collision verification via MCP.

Overview

Publisherarjun988
Repositoryblender-skills
Skill nameexport-pipeline
Stars
384
Forks
22
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by arjun988 on GitHub. Read the source before you install it.

Installation

Install the Export Pipeline AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/arjun988/blender-skills/tree/main/.claude/skills/export-pipeline
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/arjun988/blender-skills.git /tmp/blender-skills
mkdir -p .claude/skills
cp -r /tmp/blender-skills/.claude/skills/export-pipeline .claude/skills/export-pipeline
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Export Pipeline in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Export Pipeline on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Export Pipeline is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Export Pipeline

Verified, engine-ready exports. Correct scale, axis, pivots, and data.

When to Use

  • Final asset delivery
  • Engine import preparation
  • Animation/rig export
  • Batch export of modular kits

Pre-Export Gate

Required: asset-optimization validation PASS before export.

Workflow

Validation PASS → Export Settings → Test Export → Engine Verify
    → Fix Issues → Final Export → Documentation

Format Selection

FormatBest For
FBXUnreal, Unity (legacy), animation
GLTF/GLBWeb, Godot, modern Unity
OBJStatic mesh interchange (no rig)
USDPipelines, VFX, multi-asset
AlembicVFX caches, sculpt animation

FBX Settings (Game Default)

Scale: 1.0
Apply Scalings: FBX All
Forward: -Z Forward
Up: Y Up
Apply Unit: ON
Mesh: ON
Armature: ON (if rigged)
Bake Animation: ON (if animated)
Path Mode: Copy (embed textures)

GLTF Settings

Format: GLB (single file) or GLTF Separate
Include: Selected Objects
Transform: +Y Up
Compression: Draco (if supported by engine)

Export Verification Matrix

CheckMethod
ScaleMeasure known dimension in engine
PivotVerify floor contact / grip point
Forward axisCompare to engine convention
NormalsCheck shading in engine
MaterialsVerify slot count and textures
AnimationPlay action in engine
CollisionImport COL_ mesh separately

Engine-Specific Notes

Unreal Engine

  • Scale 1.0 = 1cm in UE (confirm project; may need 0.01 export scale)
  • Import normals and tangents
  • Separate collision mesh import
  • LOD naming for auto-LOD: SM_Asset_LOD0

Unity

  • Scale 1.0 typically correct
  • GLTF preferred for modern pipelines
  • Humanoid rig mapping for characters

Godot

  • GLTF/GLB preferred
  • +Y up default

Collision Export

1. Export render mesh separately from collision
2. Collision: simple convex or box
3. Name: SM_Asset_COL
4. No materials on collision mesh
5. Apply transforms before export

Animation Export

  • Single action per export file (or document action list)
  • Sample rate: 30fps default
  • Bake constraints before export
  • Include armature + skinned mesh in same file
  • No unapplied scale on rig

Batch Export (Modular Kits)

1. Select COL_Export collection
2. Export each module OR combined atlas per project spec
3. Maintain consistent origin per module type
4. Document grid snap points in README

MCP Integration

  1. Select export collection via MCP
  2. Configure export settings via MCP
  3. Execute export via MCP
  4. Verify output file exists
  5. Log export settings in delivery documentation

Delivery Documentation Template

markdown
## Export Package: [Asset Name]

**Format:** FBX / GLTF
**Scale:** 1 Blender unit = 1 meter
**Forward:** -Y / +X (document actual)
**Files:**
- SM_Asset.fbx
- T_Asset_BC.png, T_Asset_N.png, ...

**Import Notes:**
- [Engine-specific steps]

**Validation:** PASS — [date]

Constraints

MUST DO

  • Pass asset-optimization before export
  • Apply transforms on export objects
  • Test import in target engine
  • Document scale and axis conventions
  • Export collision separately for games

MUST NOT DO

  • Export with unapplied scale
  • Export without validation
  • Mix collision and render in same export without documentation
  • Assume default FBX settings work for all engines
  • Export all modifiers without testing engine result

Reference Guide

TopicReferenceLoad When
Engine importreferences/engine-import.mdFirst import test
Validation../references/validation-checklist.mdPre-export gate

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Export Pipeline AI skill do?

Production export from Blender to FBX, GLTF, OBJ, USD, and Alembic with scale, pivot, rotation, normals, materials, animation, and collision verification via MCP.

Why use Export Pipeline on TypingMind?

Because you install it once and use it with any model. Export Pipeline is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Export Pipeline in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/arjun988/blender-skills/tree/main/.claude/skills/export-pipeline. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Export Pipeline?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Export Pipeline?

As many as you like. As long as a model supports skills, you can use Export Pipeline with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Export Pipeline AI skill free?

Yes. It is published on GitHub by arjun988 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇