Contour To Mesh logo

Contour To Mesh

Community
RobLe3
contour-to-mesh

Build Blender mesh surfaces directly from extracted 2D contours/masks instead of approximate primitives. Use for 1:1 mascot/logo reconstruction, exact leaf/petal silhouettes, filled wireframe shapes, shallow bas-relief forms, or when the model outline must match a front template before adding depth.

Overview

PublisherRobLe3
Repositorycc-blender-skill
Skill namecontour-to-mesh
Stars
131
Forks
14
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 RobLe3 on GitHub. Read the source before you install it.

Installation

Install the Contour To Mesh 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/RobLe3/cc-blender-skill/tree/main/plugin/skills/contour-to-mesh
  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/RobLe3/cc-blender-skill.git /tmp/cc-blender-skill
mkdir -p .claude/skills
cp -r /tmp/cc-blender-skill/plugin/skills/contour-to-mesh .claude/skills/contour-to-mesh
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contour To Mesh 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 Contour To Mesh 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 Contour To Mesh 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.

MCP backend

Use when: Source-locked contour-derived meshes, silhouette-first modeling, triangulated mask/contour surfaces, mesh generation from OpenCV contours, or replacing generic ellipses/primitives with measured shapes.

Before the first Blender call, read ../text-to-blender/references/mcp-backends.md. Prefer official MCP for shared capabilities; preserve the selected backend for the whole task. Tool names in recipes are client/legacy examples: map them through that reference and its agent-host guide.

Contour to Mesh

Use this when a reference silhouette is the contract. The mesh starts as a filled 2D contour in front-view X/Z, then gets shallow Y depth/crown after validation.

Workflow

  1. Extract or select a clean contour/mask for one structural part.
  2. Generate a triangulated mesh recipe with scripts/mask_to_mesh_recipe.py.
  3. Run the generated Blender Python to create a named GEO_* mesh.
  4. Assign front-projected UVs immediately.
  5. Add depth only as a modifier or vertex displacement that preserves X/Z boundary positions.
  6. Validate the front render against the source mask.

Hard rules

  • Do not use radial duplication unless the manifest says the source is symmetric.
  • Do not use a generic ellipse if a contour exists.
  • Boundary vertices must keep source X/Z coordinates.
  • Depth deformation may move Y and inner vertices, but must not alter front silhouette.
  • One structural source part should become one named structural mesh.

Blender pattern

Generated mesh coordinates should map image x to Blender X and image y to Blender Z with vertical flip. Use Y only for thickness/depth.

Front-plane rotation rule

In this Blender coordinate convention, the front camera looks along the Y axis and the reference silhouette lives in the X/Z plane. Therefore 2D rotations inside the front view are rotations around the Y axis, not around Z. Use rotation_euler = (0, angle, 0) for 2D component orientation in the front projection. Z rotation spins objects into/out of screen-space incorrectly for X/Z-plane meshes.

Sources distilled

  • Blender Mesh API: create meshes from vertices/faces using from_pydata.
  • Blender BMesh: use for cleanup, triangulation, normals, smoothing.
  • OpenCV contours: detect and simplify boundaries.
  • Delaunay triangulation: useful for filled interior meshes when filtered by mask containment.

Part-inventory handoff

When masks come from source-part-segmentation, preserve the part_inventory.json names in Blender: GEO_<part_name>, MAT_<part_name>, and UV layer names. Mesh generation must record:

  • source image size;
  • source mask path;
  • contour boundary point count;
  • boundary landmark points (tip, base-left, base-right, centroid/extrema) when detectable;
  • atlas UV rectangle or projection mode.

For exact mascot/logo work, generate boundary vertices from the contour and add interior vertices only for surface support. The boundary is a contract: bevels, solidify, subdivision, shrinkwrap, or sculpt passes must not move front-view X/Z boundary vertices unless a new source mask is produced.

Hole and stroke policy

  • Filled structural masks become meshes.
  • Wireframe strokes guide boundaries/landmarks; they are not structural meshes unless the manifest classifies them as decorative linework.
  • Holes/negative regions should be kept as separate cut masks when they affect silhouette; otherwise implement them as decals/material masks.

Source-locked front-skin fallback

When a design sheet is painterly/stylized and separate orthographic views are not CAD-consistent, use a front-skin pass before sculptural interpretation:

  1. choose the canonical front/master source;
  2. extract the visible subject mask as a filled contour;
  3. create a shallow 2.5D mesh whose X/Z boundary is that contour;
  4. assign full-image front-projected UVs so the rendered front matches the source pixels;
  5. add depth only along Y and behind the front surface;
  6. optionally add separate relief/backing parts for side plausibility, but keep the front skin as the visual acceptance gate.

This is a generic fallback for logos/mascots where a faithful front read is more important than speculative volume. Mark it as front_locked_visual_skin, not as a fully solved turntable model.

Script

  • scripts/source_locked_skin_recipe.py extracts a largest/canonical foreground component and emits a mask + contour mesh recipe using full-image front-projected UV coordinates.

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 Contour To Mesh AI skill do?

Build Blender mesh surfaces directly from extracted 2D contours/masks instead of approximate primitives. Use for 1:1 mascot/logo reconstruction, exact leaf/petal silhouettes, filled wireframe shapes, shallow bas-relief forms, or when the model outline must match a front template before adding depth.

Why use Contour To Mesh on TypingMind?

Because you install it once and use it with any model. Contour To Mesh 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 Contour To Mesh in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RobLe3/cc-blender-skill/tree/main/plugin/skills/contour-to-mesh. 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 Contour To Mesh?

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 Contour To Mesh?

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

Is the Contour To Mesh AI skill free?

Yes. It is published on GitHub by RobLe3 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 👇