Retopology logo

Retopology

Community
arjun988
retopology

Production retopology for animation-ready, low-poly, quad-dominant meshes with proper edge loops and efficient polygon flow. Use after sculpting or high-poly modeling before rigging and UV work in Blender via MCP.

Overview

Publisherarjun988
Repositoryblender-skills
Skill nameretopology
Stars
384
Forks
22
Bundled files
2
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.

  • 2 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 Retopology 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/retopology
  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/retopology .claude/skills/retopology
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Retopology 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 Retopology 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 Retopology 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.

Retopology

Clean, purposeful topology for deformation, UVs, and performance. Quad-dominant. Animation-ready.

When to Use

  • After sculpting high-poly characters/creatures
  • Before rigging any deforming mesh
  • Poly reduction while preserving silhouette
  • Fixing topology from boolean or scan cleanup

Workflow

High-Poly Reference → Guide Setup → Block Retopo → Loop Refinement
    → Pole Placement → Triangle Cleanup → Validation → UV Handoff

Retopology Methods

MethodBest ForSpeed
Manual (Poly Build tool)Hero charactersSlow, best quality
Shrinkwrap retopoCreatures, organicMedium
Quad Remesh (voxel)Quick blockout retopoFast, needs cleanup
Instant Meshes (external)Background assetsFast
Symmetry retopoBilateral charactersMedium

Production default: Manual with shrinkwrap for hero; Quad Remesh + cleanup for background.

Edge Loop Rules

  • Loops follow muscle/deformation direction
  • One loop per major form change
  • Maintain even edge length in deformation zones
  • Redirect loops at poles (minimum 3 edges meeting)
  • Hide poles at back of head, armpits, groin

Pole Management

LocationAcceptableAvoid
Top of head3–5 pole—
Inner eye cornerRedirect polePole directly at corner
Shoulder3-edge pole hiddenStar pattern on deltoid
Back of kneePole in creasePole on front of knee

Triangle Policy

  • Triangles OK on non-deforming static mesh
  • Convert tris to quads on face, joints, fingers
  • No n-gons on deforming surfaces
  • Tris at hidden areas (scalp under hair, mouth interior)

Polycount Targets

See ../references/polycount-budgets.md. Retopo is where budget is enforced.

Shrinkwrap Retopo Setup

1. Duplicate high-poly to reference collection (hidden in render)
2. Create retopo mesh with Poly Build / manual extrude
3. Shrinkwrap modifier → Target: high-poly
4. Snap to face with project individual elements
5. Validate shrinkwrap distance (no intersection)

Validation Checklist

  • Quad-dominant on all deformation areas
  • Edge loops support planned rig joints
  • No non-manifold geometry
  • Silhouette matches high-poly reference
  • Polycount within budget
  • Poles placed at acceptable locations
  • Mesh manifold and watertight (if required)

MCP Integration

  1. Create retopo mesh object via MCP
  2. Apply shrinkwrap modifier via MCP
  3. Query face/edge count during retopo
  4. Compare silhouette via MCP render/query
  5. Transfer to COL_Geo_LowPoly collection

Constraints

MUST DO

  • Retopo before rigging deforming meshes
  • Preserve silhouette vs high-poly reference
  • Plan loops for facial expressions (characters)
  • Enforce polycount budget
  • Validate manifold before UV pass

MUST NOT DO

  • Auto-retopo without manual cleanup (hero assets)
  • Leave n-gons on deformation surfaces
  • Skip validation against reference
  • Retopo without knowing rig requirements
  • Uniform density (more density at face/hands)

Reference Guide

TopicReferenceLoad When
Facial retoporeferences/facial-retopo.mdCharacter faces
Game vs cinematicreferences/game-cinematic-topo.mdBudget decisions

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 Retopology AI skill do?

Production retopology for animation-ready, low-poly, quad-dominant meshes with proper edge loops and efficient polygon flow. Use after sculpting or high-poly modeling before rigging and UV work in Blender via MCP.

Why use Retopology on TypingMind?

Because you install it once and use it with any model. Retopology 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 Retopology in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/arjun988/blender-skills/tree/main/.claude/skills/retopology. 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 Retopology?

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 Retopology?

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

Is the Retopology 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 👇