Agent skill

Model Compare

Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall).

Install Model Compare

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/build123d/skills/model-compare .claude/skills/model-compare && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .claude/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/build123d/skills/model-compare .agents/skills/model-compare && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .agents/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/build123d/skills/model-compare .cursor/skills/model-compare && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .cursor/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/rawwerks/VibeCAD.git --path plugins/build123d/skills/model-compare

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/build123d/skills/model-compare .gemini/skills/model-compare && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .gemini/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/build123d/skills/model-compare .github/skills/model-compare && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .github/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rawwerks/VibeCAD --skill model-compare -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install rawwerks/VibeCAD model-compare --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rawwerks/VibeCAD.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/build123d/skills/model-compare .opencode/skills/model-compare && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "model-compare" agent skill from https://github.com/rawwerks/VibeCAD/tree/main/plugins/build123d/skills/model-compare into .opencode/skills/model-compare/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compare", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: model-compare
GitHub stars: 121
Token cost: ~1.4k tokens
SKILL.md length: 246 words
Files: 2 (incl. scripts)
Skills in repo: 4
Repo updated: Jan 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall).

Evaluating generated models against gold references
SKILL.md covers Quick Start, Supported Formats, Output Metrics and CLI Options, plus 5 more sections
Runs Python scripts from its folder; calls uvx and jq
Diffing CAD revisions

What it does

Model Compare is an agent skill from rawwerks/VibeCAD. Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/model_diff.py`).

It sits in Game Development, covering 3D graphics and WebGL. The repository describes itself as: A library of Claude Code skills for teaching coding agents how to use various CAD tools. The licence is MIT.

When your agent uses it

Evaluating generated models against gold references
Diffing CAD revisions
Computing similarity metrics for ML training
Intersection over union

Example prompts

“/model-compare”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 609e888. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- uvx
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uvx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Compare loads about 1.4k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 246 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~103
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from rawwerks/VibeCAD at commit 609e888, republished under its MIT licence (© rawwerks). 246 words, ~1,367 tokens.

Download SKILL.mdSave it as .claude/skills/model-compare/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: model-compare
description: Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.

3D Model Comparison Tool

Compare CAD models using boolean operations to compute similarity metrics like IoU, Dice, precision, and recall. Useful for:

Evaluating ML-generated models against gold references
Comparing revisions of CAD designs
Computing metrics for training 3D generative models
Visualizing geometric differences

Quick Start

bash

# Compare two STEP files
uvx --from build123d python scripts/model_diff.py reference.step generated.step

# JSON output for training pipelines
uvx --from build123d python scripts/model_diff.py ref.step gen.step --json --no-export

# Demo mode (no files needed)
uvx --from build123d python scripts/model_diff.py --demo

Supported Formats

Format	Extension	Notes
STEP	`.step`, `.stp`	Recommended - full CAD fidelity
BREP	`.brep`	OpenCASCADE native format
STL	`.stl`	Mesh format - may have boolean issues

Output Metrics

Primary Metrics (for ML training)

Metric	Range	Description
IoU (Jaccard)	0-1	`
Dice (F1)	0-1	`2
Precision	0-1	`
Recall	0-1	`

Diagnostic Metrics

Metric	Description
`volume_ratio`	B/A volume ratio (1.0 = same size)
`center_offset`	Distance between centers of mass
`bbox_iou`	Bounding box IoU (coarse alignment)
`size_ratio_x/y/z`	Per-axis scale comparison
`surface_ratio`	Surface area comparison

Interpretation

The tool provides automatic interpretation:

Over-generating: Low precision, high extra geometry
Under-generating: Low recall, missing geometry
Size issues: Volume ratio far from 1.0
Position issues: Large center offset

CLI Options

usage: model_diff.py [-h] [-o OUTPUT_DIR] [--json] [--no-export] [--demo]
                     [reference] [generated]

positional arguments:
  reference          Reference/gold model file (STEP, BREP, or STL)
  generated          Generated/predicted model file to compare

options:
  -o, --output-dir   Output directory for GLB files (default: .)
  --json             Output only JSON metrics (for pipelines)
  --no-export        Skip exporting GLB visualization files
  --demo             Run with built-in demo models

Output Files

When --no-export is not set, produces GLB files for visualization:

File	Description
`diff_reference.glb`	The reference model (A)
`diff_generated.glb`	The generated model (B)
`diff_missing.glb`	Geometry in A but not B (under-generation)
`diff_extra.glb`	Geometry in B but not A (over-generation)
`diff_common.glb`	Geometry in both (correct match)

Example: Training Pipeline Integration

bash

# Batch evaluation
for gen in outputs/*.step; do
    uvx --from build123d python model_diff.py gold.step "$gen" --json --no-export
done | jq -s '{
    avg_iou: (map(.iou) | add / length),
    avg_precision: (map(.precision) | add / length),
    avg_recall: (map(.recall) | add / length)
}'

Example: Loss Function

python

# In your training code, use metrics for loss:
loss = (
    (1 - metrics['iou']) * 1.0 +           # Primary shape match
    abs(1 - metrics['volume_ratio']) * 0.5 + # Scale accuracy
    metrics['center_offset'] * 0.1           # Position accuracy
)

How It Works

The tool uses boolean operations from OpenCASCADE (via build123d):

Missing  = Reference - Generated  (A - B)
Extra    = Generated - Reference  (B - A)
Common   = Reference & Generated  (A ∩ B)
Union    = Reference + Generated  (A ∪ B)

IoU      = volume(Common) / volume(Union)
Dice     = 2 * volume(Common) / (volume(A) + volume(B))
Precision = volume(Common) / volume(B)
Recall    = volume(Common) / volume(A)

Sample Output

=================================================================
  3D MODEL COMPARISON REPORT
  Reference (A) vs Generated (B)
=================================================================

──────────────────────────── VOLUMES ────────────────────────────
  Reference (A):          51,433.629
  Generated (B):          45,904.426
  Intersection (A∩B):     42,292.031
  Missing (A-B):           9,141.598  (17.8% of A)
  Extra (B-A):             3,612.395  (7.9% of B)

──────────────────────── PRIMARY METRICS ────────────────────────
  IoU (Jaccard):              0.7683  (1.0 = identical)
  Dice (F1):                  0.8690  (1.0 = identical)
  Precision:                  0.9213  (correctness of B)
  Recall:                     0.8223  (coverage of A)

──────────────────────── INTERPRETATION ─────────────────────────
  △ Partial match (IoU > 50%)
  → Under-generating: 17.8% of A is missing
  → Undersized by 10.8%
=================================================================

Files

SKILL.md and 1 other file (scripts) in plugins/build123d/skills/model-compare of rawwerks/VibeCAD.

SKILL.md
scripts/model_diff.py

Open the folder on GitHubat commit 609e888

Compare with similar skills

Model Compare next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Model Compare compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Model Compare this skillrawwerks/VibeCAD	121	—	~1.4k	Automated safety check: Pass	MIT	9 mo ago
Image to Three.js Modelimg2threejs/img2threejs	18k	1 repos	~8.2k	Automated safety check: Pass	Apache-2.0	yesterday
Web CloneJane-xiaoer/claude-skill-web-clone	1k	1 repos	~2.7k	Automated safety check: Pass	MIT	3 mo ago
Threejs Game Directormajidmanzarpour/threejs-game-skills	2.5k	—	~2.2k	Automated safety check: Pass	MIT	11 days ago
Game Asset Generatorhtdt/godogen	7.1k	—	~2.8k	Automated safety check: Pass	MIT	7 days ago
Threejs Gameplay Systemsvalkor-ai/loom	1.2k	1 repos	~1.4k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
18k GitHub starsUsed in 1 repo~8.2k tokens
Game DevelopmentAuto-check passed
Web Clone
Jane-xiaoer/claude-skill-web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说复刻网站、克隆网站、clone website、抄个站、仿站、照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 /…
1k GitHub starsUsed in 1 repo~2.7k tokens
Game DevelopmentAuto-check passed
Threejs Game Director
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
2.5k GitHub stars~2.2k tokensUpdated 11 days ago
Game DevelopmentAuto-check passed
Game Asset Generator
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
7.1k GitHub stars~2.8k tokensUpdated 7 days ago
Game DevelopmentAuto-check passed
Threejs Gameplay Systems
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
1.2k GitHub starsUsed in 1 repo~1.4k tokens
Game DevelopmentAuto-check passed
Threejs World Generation
calesthio/OpenMontage
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.
66k GitHub stars~2k tokensUpdated 5 days ago
Game DevelopmentAuto-check passed

Questions about Model Compare

What does Model Compare do?

Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Model Compare is an agent skill from rawwerks/VibeCAD. Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall).

When should I use Model Compare?

Model Compare fits situations like: evaluating generated models against gold references; diffing CAD revisions; computing similarity metrics for ML training; intersection over union.

How do I install Model Compare in Claude Code?

Run `npx skills add rawwerks/VibeCAD --skill model-compare -a claude-code`. Or copy the skill folder (plugins/build123d/skills/model-compare in rawwerks/VibeCAD) into .claude/skills/model-compare in your project. Claude Code loads it when a task matches its description.

How do I install Model Compare in Codex?

Run `npx skills add rawwerks/VibeCAD --skill model-compare -a codex`. Or copy the skill folder (plugins/build123d/skills/model-compare in rawwerks/VibeCAD) into .agents/skills/model-compare in your project. Codex loads it when a task matches its description.

Can I use Model Compare in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rawwerks/VibeCAD --skill model-compare -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-compare, .gemini/skills/model-compare, .github/skills/model-compare and .opencode/skills/model-compare in your project.

What does Model Compare need to run?

Going by SKILL.md and its folder, Model Compare needs Python for the scripts in its folder and the command-line tools its instructions call (uvx and jq). Our summary lists: Python 3.

Does Model Compare access the network?

SKILL.md contains no URLs. Its commands use uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Model Compare safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Model Compare use?

Model Compare is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Model Compare use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Model Compare?

Skills that share tags, products or a category with Model Compare: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Compare?

rawwerks (a GitHub user) maintains it in rawwerks/VibeCAD, which has 121 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on January 5, 2026.

Source: rawwerks/VibeCAD on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Model Compare

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

3D Model Comparison Tool

Quick Start

Supported Formats

Output Metrics

Primary Metrics (for ML training)

Diagnostic Metrics

Interpretation

CLI Options

Output Files

Example: Training Pipeline Integration

Example: Loss Function

How It Works

Sample Output

Files

Compare with similar skills

Similar skills

More from rawwerks/VibeCAD

Related

Questions about Model Compare