MCP servers and skills: search, filter by where they run, and compare.
A professional AI development skill that trains coding agents and LLMs to design, build, test, and deploy modern premium websites with advanced animations and 3D interactive experiences
SkillMIT★ 4Few starsNo key
Agent skill: turn any flat logo into a premium 3D spinning coin (React Three Fiber). One command, try it live in your browser.
SkillMIT★ 4Few starsNo key
Drop a full augmented-reality studio into any web page. Place any number of 3D models in your real room through the camera, generate new ones from a text prompt, arrange them, then share the scene as
Node.jsApache-2.0★ 8No key
Build Meshy 3D agent skills to generate, texture, rig, animate, and prep 3D models for print without an MCP server
SkillMIT★ 5No key
The first AI skill pack for 3D pre-production reference workflows — ref briefs, style decoding, board audits, marketplace briefs, client alignment. Free forever. MIT.
SkillMIT★ 13No key
AI agent operating system for Blender 5.2: bpy knowledge base, AGENT_OK execution contract, 3D-print production gate, worked keyboard and desktop-robot builds.
PythonMIT★ 96No key
One-prompt 3D brain-region figures & rotating glow animations from 200+ BrainGlobe atlases (any species), rendered headless in Blender. A low-token Claude Code skill.
SkillMIT★ 9No key
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone
OfficialSkillApache-2.0★ 3.6k in collectionNo key
3D printing toolkit — AI-powered design skills for Claude Code, Cursor, Windsurf & Copilot, plus parametric OpenSCAD models
SkillMIT★ 6No key
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video file
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Claude skill: turn your own MAME arcade ROM into a Three.js 3D remaster — original code runs unmodified, sound remastered. EN/KO
SkillMIT★ 4Few starsNo key
AETumi MCP — install premium, production-ready Three.js/WebGL 3D web components into Claude Code, Cursor & Codex. Premium 3D web you own, from AETumi (aetumi.app).
Hosted by authorMIT★ 1Few starsNo key
Agent skill for creative 3D visualization: turn an idea into a Three.js/Blender scene worth exploring. Claude Code + Codex plugin, 223 recipes, 440 knowledge records, 22 proved kits, 37 runnable studi
SkillMIT★ 788No key
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end 3D perception, with an instance bank for
OfficialSkillApache-2.0★ 3.6k in collectionNo key
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evalu
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Awwwards-style scroll-driven 3D website skill for Claude Code (Three.js r170 + GSAP + Lenis)
SkillMIT★ 27No key
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custo
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Claude Code 股票智能分析 Skill — 3D 评分（技术 50 + 基本面 30 + 消息面 20）。Fork from @liusai0820/Stock-Analysis-Skill with extensive enhancements.
SkillMIT★ 4Few starsNo key
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
3D & AR SDK for Android (Jetpack Compose + Filament), Apple (SwiftUI + RealityKit), Web, Flutter and React Native. Opens glTF/GLB, 3MF, STL, OBJ and PLY on Android and USDZ on Apple, at real size in A
Node.jsApache-2.0★ 1.3kNo key
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and rob
OfficialSkillApache-2.0★ 3.6k in collectionNo key
One entry point for Claude Code over pinned open-source Blender skill libraries: registry, workflows, profiles, single Blender MCP server
SkillMIT★ 6No key
Authoring and debugging scripts for Rhinoceros 3D (Rhino 8 and later). Use when asked to write RhinoScript (VBScript / .rvb / .vbs), RhinoPython, or RhinoCommon-based scripts; automate Rhino modeling
OfficialSkillMIT★ 40k in collectionNo key
Who stands behind it
