Claude 3d Harness

Entry point for every 3D or Blender task - modeling, materials, lighting, cameras, rendering, animation, product shots, environments, cinematic scenes, exports. Classifies the job (fast, standard or cinematic), picks a workflow, asks the harness registry which library skills to load, then drives Blender through the harness's single Blender MCP server with render, inspect and refine checkpoints. Use it whenever the user asks to create, change, light, render, animate or export anything in 3D, even if they never say "Blender".

8 starsImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add MAX-786/claude-3d-harness --skill claude-3d-harness

Manual install

git clone --depth 1 https://github.com/MAX-786/claude-3d-harness.git /tmp/claude-3d-harness
mkdir -p ~/.claude/skills
cp -r /tmp/claude-3d-harness/. ~/.claude/skills/claude-3d-harness

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# claude-3d-harness

The user's request: $ARGUMENTS

If the request is empty, ask what they want to build before doing anything else.

The 3D skills live in `library/`: five skill libraries by different authors,
kept in this repository, security-reviewed and checksummed. They overlap (two
ship a `blender-lighting`), were written for different MCP servers, and one is
in Italian. The registry settles all of that: one provider per capability, one
MCP server, and a note for every adaptation you need to make. So never browse
`library/` to choose skills yourself. Ask the registry, then read exactly what
it names.

## Where things are

- **Harness root.** Written `H` below. It is `${CLAUDE_PLUGIN_ROOT}`, which
  Claude Code fills in when the harness is installed as a plugin. If you see
  that placeholder literally instead of a path, you are working in a clone of
  the repository, and `H` is the repository root: the folder that holds this
  file and `registry/`.
- **Engine.** `uv run "H/scripts/harness.py" <command>` works from any directory.
  Paths in its output are relative to `H`, which it prints on the first line.
- **Job folders.** `output/<yyyymmdd-hhmm>-<slug>/` inside the user's project
  (`${CLAUDE_PROJECT_DIR}`, or the current directory in a clone), never inside
  `H`. The Blender MCP server uses the same `output/` folder as its workspace.
- **Tool names.** The harness runs one Blender MCP server, named `blender`.
  Installed as a plugin, its tools appear as

Read the full skill on GitHub

Details

Skill name: claude-3d-harness
Repository: MAX-786/claude-3d-harness
License: MIT
Repo updated: 21 September 2026

FAQ

What does the Claude 3d Harness skill do?

How do I install the Claude 3d Harness skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add MAX-786/claude-3d-harness --skill claude-3d-harness. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Claude 3d Harness popular?

It lives in MAX-786/claude-3d-harness, which has 8 GitHub stars and 0 forks.

Related skills

Diagram to Image

zju-zhanglu/diagram-to-image

Convert Markdown documents containing ASCII or Unicode text diagrams into faithful draw.io PNG images. Use when the user provides a Markdown file or Markdown text and asks to extract architecture diagrams, flowcharts, or sequence diagrams from fenced or indented text blocks, generate draw.io XML through the drawio MCP, review and lint XML, gate export through browser-based human approval, and export PNGs.

Images, Video & Audio

Book Distill

ilia-pluzhnikov/book-distill

Перегоняет длинный материал — книгу, транскрипт видео, подкаст, курс, интервью, лонгрид — в набор атомарных вызываемых скиллов: фреймворки, принципы, чек-листы, решающие процедуры и границы их применения. Вызывать, когда просят «разбери книгу на скиллы», «сделай скилл из этой книги», «вытащи методичку из курса», «turn this book into skills», «distill this podcast into reusable skills», «extract frameworks from this course» — то есть нужны рабочие методы из источника, а не его пересказ. НЕ для саммари и рецензий, НЕ для отыгрыша автора, НЕ для восстановления книги по памяти без текста.

Images, Video & Audio

Hyperframes Motion

2boysfromtown/hyperframes-motion

Make After Effects-style motion graphics in plain HTML + GSAP — 3D camera moves, kinetic typography, cinematic transitions and four ready-to-edit 1080x1920 templates. Use when the user wants an animated product reveal, social-media ad, brand story or kinetic-text video built as a web page, or asks for "motion graphics", "animated title", "cinematic text" or a 9:16 video template.

Images, Video & Audio

Blender Campaign Studio

Meir770ar/blender-campaign-studio

Direct, produce and edit Hebrew commercials, brand films and campaign videos in Blender: adaptive interview, direction, editorial, reusable HeyGen Avatar IV/V characters and Digital Twins, Codex images, Grok subscription video through the native SDK including mode-aware 1080p, Suno music, ElevenLabs or Gemini 3.8 TTS narration, ElevenLabs sound effects, HyperFrames HTML motion graphics, AAA/RTL typography, sound/color finishing in Blender or DaVinci Resolve Studio (plan hand-off, MCP finishing, verified import) and compressed WhatsApp self-delivery. Natural Hebrew: תכין לי סרטון, תערוך לי סרטו

Images, Video & Audio

Img2img Studio

Dogwind221/img2img-studio

图生图工作室：先识图分析输入图片，再按风格模式生成新图。触发：用户给出/上传图片并要求「生成类似风格的新图」「换个风格重绘」「图生图」「以这张图为基础出图」「做成电商图/套图/主图/详情页」「杂志编辑风/抽象艺术/手绘插画/废片焕新」。不触发：只是「描述/分析图片」而不要求生成新图（那属于 dsh-vision-skill）。模式：photo-art（editorial 编辑杂志风 / revival 白纸手绘风 / 融合风）与 ecommerce（商品主图、卖点图、场景图、详情页、PDP、Amazon/Shopify 图包）。生图通道一级优先 ChatGPT 网页（image 2.5）：免费网页账号先用，额度用尽后自有账号（Codex/Plus）优先，再降级 API（DashScope qwen-image-3.0-pro、OpenAI gpt-image、Z.AI、Seedream、MiniMax）；支持 t2i/i2i、批量并发、质量预设。

Images, Video & Audio

AI Video Producer

zysilm/ai-video-producer-skill

Complete AI video production workflow using WAN 2.1 and Qwen Image Edit 2511 models via ComfyUI. Creates any video type: promotional, educational, narrative, social media, animations, game trailers, music videos, product demos, and more. Use when users want to create videos with AI, need help with video storyboarding, keyframe generation, or video prompt writing. Follows a philosophy-first approach: establish visual style and production philosophy, then execute scene by scene with user feedback at each stage. Supports advanced features like layer-based compositing, reference-based generation,

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.