Skip to content
Research
Skill

/3dgs-engineering-guide

Guide for deploying 3DGS from research to production: 10 industry verticals, engineering stack, GIS toolchain solutions, cross-platform deployment, and common pitfalls. References 976 methods. Use when: deploying 3DGS to production or industry, selecting tools/pipeline/platform,

BOOST
From plugin
awesome-gaussian-skills
16518 skills
Install
$ npx -y skills add jaccen/Awesome-Gaussian-Skills --skill 3dgs-engineering-guide --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/3dgs-engineering-guide

Context preview

The summary Claude sees to decide when to auto-load this skill.

Guide for deploying 3DGS from research to production: 10 industry verticals, engineering stack, GIS toolchain solutions, cross-platform deployment, and common pitfalls. References 976 methods. Use when: deploying 3DGS to production or industry, selecting tools/pipeline/platform,

SKILL.md

3dgs-engineering-guide.SKILL.md
name: 3dgs-engineering-guide
description: 'Guide for deploying 3DGS from research to production: 10 industry verticals, engineering stack, GIS
  toolchain solutions, cross-platform deployment, and common pitfalls. References 1011 methods. Use when: deploying
  3DGS to production or industry, selecting tools/pipeline/platform, troubleshooting engineering problems (OOM,
  artifacts, platform lock-in), integrating 3DGS with GIS/BIM/ROS2/game engines, 3DGS部署/高斯泼溅工程化/3DGS生产环境/工程指南.'
license: Apache-2.0
metadata:
  version: 2.0.0
  author: jaccen
  tags:
  - 3dgs
  - gaussian-splatting
  - engineering
  - deployment
  - digital-twin
  - autonomous-driving
  when_to_use:
  - Deploy 3DGS to production or an industry application
  - Select tools, pipeline, or platform for a 3DGS deployment scenario
  - Troubleshoot engineering problems with 3DGS (OOM, artifacts, platform lock-in)
  - Integrate 3DGS with GIS, BIM, ROS2, or game engines
  - 3DGS部署 / 高斯泼溅工程化 / 3DGS生产环境 / 工程指南
  platform-fields:
    user-invocable: true

3DGS Engineering Guide (Router)

> **Architecture**: Axis-driven static/dynamic router. Do NOT try to apply the engineering guidance from memory or from this router alone. Always load fragments from disk as described below.

Step 1 — Detect Request Axes

Analyze the user's request to determine axis values:

Axis: domain

| User Intent | domain value | |-------------|-------------| | Autonomous driving simulation, sensor sim | autonomous-driving | | Digital twin, smart city, GIS | digital-twin | | Cultural heritage, museum, 3D archiving | culture | | Film, game production, virtual production | film-games | | E-commerce, 3D product display, WebAR | ecommerce | | Industrial inspection, drone survey | industrial | | AR/VR/MR headsets, spatial computing | ar-vr | | BIM, architecture, as-built verification | bim | | Robotics, embodied AI, manipulation | robotics | | Military simulation, defense | military | | World model, interactive 3D world | world-model | | Unspecified or broad engineering question | all |

Axis: focus

| User Intent | focus value | |-------------|-------------| | Data acquisition, reconstruction, deployment pipeline | pipeline | | Quality assurance, scalability, cross-platform | best-practices | | Debugging artifacts, OOM, deployment failures | pitfalls | | Choosing tools by use case/platform/scale | decision-tree | | Specific technology stack info (formats, compression, engines) | tech-stack | | GIS integration, spatial analysis, S3M/Cesium | gis-toolchain | | Unspecified or comprehensive engineering guidance | all |

If the user does not specify, defaults are: domain=all, focus=all.

Step 2 — Load Required Fragments

Always Load (every invocation)

Read these files from static/:

  • static/core-stance.md — Role, workflow, deployment scale reference, terminology, guardrails

On-Demand Load (by detected domain)

All domain values load `static/industry-landscape.md` (the landscape fragment covers all 10 verticals + world models). The Router will focus attention on the relevant section within the loaded fragment.

On-Demand Load (by detected focus)

| focus | Fragment(s) to Load | |-------|-------------------| | pipeline | static/tech-stack.md | | best-practices | static/best-practices.md | | pitfalls | static/pitfalls.md | | decision-tree | static/decision-trees.md | | tech-stack | static/tech-stack.md | | gis-toolchain | static/gis-toolchain.md | | all | All focus fragments (tech-stack, best-practices, pitfalls, decision-trees, gis-toolchain) |

Reference Load (when citing specific methods)

  • static/reference-papers.md — Method tables organized by domain

**Optimization**: For a focused question (e.g., "how to deploy 3DGS on Quest 3"), load core-stance + industry-landscape (domain=ar-vr section) + tech-stack. For broad planning (e.g., "start a digital twin project"), load all fragments.

Step 3 — Execute Engineering Guidance

After loading the required fragments:

1. Identify use case from domain axis — focus on the relevant industry section 2. Recommend pipeline from tech-stack fragment 3. Reference specific methods from reference-papers fragment and knowledge base 4. Provide concrete next steps — actionable items, not generic advice 5. Warn about pitfalls from pitfalls fragment — highlight domain-specific failure modes

Cross-Skill Routing

This skill focuses on production engineering. For related workflows:

  • **Method comparison** → 3dgs-method-compare (for selecting methods for deployment)
  • **Code review/bug detection** → 3dgs-code-reviewer (for detecting deployment-critical bugs)
  • **MCP rendering** → 3dgs-mcp-renderer (for real-time rendering integration)
  • **Spatial intelligence** → 3dgs-spatial-agent (for agent-driven deployment scenarios)
  • **CAD/Mesh integration** → cad-mesh-3dgs (for BIM/CAD workflows)

Red Lines

The following are categorical prohibitions. Violating any of these invalidates the output:

  • **No invented data**: Never fabricate deployment metrics, VRAM numbers, or system requirements not in the loaded reference files. If a value is not found, write "data not available" or "N/A".
  • **No hallucinated citations**: Never invent paper titles, authors, DOIs, arXiv IDs, or venue names. Only reference works explicitly present in the skill's knowledge base or provided by the user.
  • **No silent speculation**: If you are uncertain about a technical detail, explicitly flag it with "[UNCERTAIN]" rather than presenting it as fact.
  • **No method misattribution**: Do not assign features, results, or mechanisms from one method to another. Each method's data is specific to that method.
  • **No oversimplified recommendations**: Do not reduce complex deployment trade-offs to a single "use this" judgment without considering the target environment.

Related Skills

  • **3dgs-method-compare** — Method comparison (use for selecting methods for deployment)
  • **3dgs-code-reviewer** — Code review (use for detecting deployme
Read more
Ships withawesome-gaussian-skills

900 arXiv-verified 3DGS methods · 15 AI agent skills · MCP server (34 tools) · open ebook — the AI-native entry to 3D Gaussian Splatting research

Get the whole plugin

Other skills on awesome-gaussian-skills.