Explorer Viewer Builder logo

Explorer Viewer Builder

CommunityPopular
mohitagw15856
explorer-viewer-builder

Use when asked to build a 3D viewer for a GLB model, make an interactive explorer with clickable labelled parts, add an exploded view or quiz to a 3D model, or turn a parts list into a web page. Produces a single-file Three.js viewer that loads GLB models, with orbit controls, clickable labelled parts, an exploded view toggle and a quiz mode, built from the tested template in references/viewer-template.html. Third step of explorer-pipeline.

Overview

Publishermohitagw15856
Repositorypm-claude-skills
Skill nameexplorer-viewer-builder
Stars
1.4K
Forks
257
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mohitagw15856 on GitHub. Read the source before you install it.

Installation

Install the Explorer Viewer Builder 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/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-3d-explorer/skills/explorer-viewer-builder
  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/mohitagw15856/pm-claude-skills.git /tmp/pm-claude-skills
mkdir -p .claude/skills
cp -r /tmp/pm-claude-skills/plugins/pm-3d-explorer/skills/explorer-viewer-builder .claude/skills/explorer-viewer-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Explorer Viewer Builder 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 Explorer Viewer Builder 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 Explorer Viewer Builder 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.

Explorer Viewer Builder

The last step of a 3D explorer is a page anyone can open: no install, no build step, works on a phone. This skill produces a single HTML file from the tested template in references/viewer-template.html: Three.js from a CDN, a GLB loader, orbit controls, clickable parts with sourced labels, an exploded view and a quiz mode, filled in with the parts list and palette from the earlier steps.

Required Inputs

Ask for these if not provided:

  • The GLB file (path or URL), or confirmation to start with the template's demo assembly
  • The parts list: mesh name, label, description and source for each part (from model-prompt-pack)
  • Palette and layout values (from explorer-interface-brief), or accept the template defaults
  • Title and the illustrative statement
  • Hosting: GitHub Pages, a static host, or opening the file locally (GLB files need a local server; browsers block file:// loading)

Output Structure

1. The viewer file

A complete index.html based on the template, with:

  • CONFIG filled in: title, model, and parts (one entry per mesh name, each with label, description and source)
  • Palette applied to the CSS custom properties, with a dark-mode block
  • The illustrative statement in the panel footer
  • unchanged core behaviour from the template: orbit controls with damping; click (or tap) to select, ignoring drags; selection through the parts list for keyboard users; exploded view that moves each part away from the model's centre in its parent's space; quiz mode that asks for a random part, scores answers and highlights the right part after a miss; reset view; a demo fallback and a console warning if the model fails to load; a list of the model's mesh names when none match the parts list

2. Mesh-name check

A table matching the parts list against the mesh names the viewer reports (open the page with the model and read the panel, or the console): | Mesh name in parts list | Found in GLB? | Action |

3. Run and publish instructions

  • Local: npx serve . (or python3 -m http.server) in the folder, then open the printed address
  • GitHub Pages: commit index.html and the .glb, enable Pages for the branch, and note the file-size limits
  • Performance: keep the GLB under 15 MB; compress textures; test on a mid-range phone

4. Test checklist

Binary checks to run in a browser: the model appears; each part in the list highlights and shows its label and source; dragging rotates without selecting; exploded view separates every labelled part and reverses; quiz mode scores a right and a wrong answer; the page has no horizontal scroll at 390 px wide; dark mode is readable; the console shows no errors.

Quality Checks

  • The output is a single HTML file with no build step
  • Every entry in CONFIG.parts has a label, a description and a source
  • Every parts-list mesh name is checked against the GLB, with mismatches listed
  • Parts can be selected from the keyboard through the parts list
  • Exploded view and quiz mode both work and can be turned off
  • The illustrative statement is visible on the page
  • The page works at 390 px width and in dark mode with no console errors
  • Three.js is loaded from a pinned version, not "latest"

Anti-Patterns

  • Opening the HTML by double-clicking with a local GLB. Browsers block it; use a local server.
  • Labels without sources. The viewer shows the source line for a reason; never leave it blank.
  • Selecting on pointer down. Every rotation then selects a part; select on a click without movement.
  • Unpinned CDN versions. A Three.js update can break the page overnight.

Example Trigger Phrases

  • "Build a viewer for heart.glb with clickable labelled parts and a quiz."
  • "Turn this parts list into a single-file Three.js explorer."
  • "Add an exploded view and quiz mode to my 3D model page."
  • "Make a GLB viewer that works on phones, no build step."

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 Explorer Viewer Builder AI skill do?

Use when asked to build a 3D viewer for a GLB model, make an interactive explorer with clickable labelled parts, add an exploded view or quiz to a 3D model, or turn a parts list into a web page. Produces a single-file Three.js viewer that loads GLB models, with orbit controls, clickable labelled parts, an exploded view toggle and a quiz mode, built from the tested template in references/viewer-template.html. Third step of explorer-pipeline.

Why use Explorer Viewer Builder on TypingMind?

Because you install it once and use it with any model. Explorer Viewer Builder 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 Explorer Viewer Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-3d-explorer/skills/explorer-viewer-builder. 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 Explorer Viewer Builder?

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 Explorer Viewer Builder?

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

Is the Explorer Viewer Builder AI skill free?

Yes. It is published on GitHub by mohitagw15856 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 👇