3DCharaMakeSkills-Lida skill
A skill pack for 3D characters from illustrations: input prep, rigging, expressions and checks in Blender.
- 64 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill is read as a guide; running CLI checks needs an explicit task to work on the model.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/3dcharamakeskills-lidaDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is read as a guide; running CLI checks needs an explicit task to work on the model.
This is third-party code. Review the repository files before installing.
What it does
The pack gathers experience of building a 3D character from references. The `lida-avatar-workflow` skill guides through stages: preparing images and three views, getting a base model, mesh repair, skeleton, weights, eyes and mouths, expressions, hands, hair, clothing, wings and materials. For the skeleton it describes the Tripo auto-rig route with FBX up to 150 MB. It includes stage guides, 28 diagrams, ready CLI checks and a finished reference model. A command success is judged only within its stated scope, while appearance, motion and saved-file reproduction are checked separately. Documentation is in Japanese and English.
Who it is for. 3D artists and VRM avatar authors who make a character from an illustration and want an agent guided through Blender step by step.
Good fit when
- An illustration of a character must become a finished 3D model.
- A generated model has mesh damage and missing parts.
- Facial animation is needed: eyes, an open mouth shape and blinking.
- A production plan with stages and completion criteria is needed.
Not a fit when
- A ready model in one click is needed: the pack describes manual refinement.
- You work on architecture or objects rather than characters.
- There is no Blender or 3D generation service.
Example request
Load lida-avatar-workflow and write a short production plan in English for a model from these three views, with mesh diagnostics.Limitations
Applications, generation services, API keys and source models are not included: you need Blender and, for example, Tripo. The finished renders show a refined result, not a guarantee of the same result from one run. The reference model in the full archive has separate terms: redistribution and resale of the archive containing it are forbidden. The repository licence is not auto-detected, so read the `LICENSE` files and the model terms. Copy the whole skill folder rather than `SKILL.md` alone.
How to disable. Delete the `lida-avatar-workflow` folder from the agent skills directory. The downloaded archive and Blender projects are deleted by hand.
FAQ
What do I copy to the skills directory?
The whole `skills/lida-avatar-workflow` folder, with guides, assets and scripts. `SKILL.md` alone will not work as intended.
Are Python and the shader needed just to read?
No, reading the guides needs neither. Reading the skill installs no software and changes no project.
How does rigging work?
The recommended route is an FBX up to 150 MB, Tripo auto-rig with the VRM 1.0 skeleton, preservation checks, then rig and weight adjustment.
Can I use the archive model in my projects?
No, it is a reference for study; redistributing the archive with the model and selling modified versions is not allowed.
Is there an English variant?
Both exist: English requests route to `SKILL.en.md` and the English guide index.
Discussion
No questions or reviews yet.
Related
SkillsA skill that takes one character sheet to a 3D model that dances in MMD: generation, rig, textures, faces, physics, render.
Turns one or two of your photos into a cartoon character and extends it into avatars, stickers and scenes with one face.
A skill and tools for Codex that turn a reference or layered PSD into a working Live2D model with checks and a web preview.
A Claude Code skill that builds a game-ready 3D asset in Blender from concept art and checks each phase by measurement.
A skill rebuilds the object in a reference image as a procedural Three.js model written in code, not downloaded art
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
README in short
A pack of guides, diagrams and CLI checks for a 3D character from an illustration. Bilingual, with a reference model and separate terms for its use.