Submit Log in

CAD

by earthtojake

MIT

Repository Docs

Featured markdown Development

cad3d-printingbuild123dstephardwareengineering

Summary

Generates and validates parametric STEP-first CAD parts and assemblies from natural language.

Features

Generates parametric build123d Python source and validated STEP artifacts from natural language
Accepts reference images and 2D technical drawings as design input
Source-level joints and named mating datums for assemblies
Sensible mechanical defaults (wall thickness, fillets, clearance holes)
Mandatory geometric validation: selector refs, planes, positioning, alignment
Mandatory snapshot review before a model is considered complete
Secondary STL / 3MF / native GLB export workflows

Install This Skill

Add this skill to your favorite AI agent in a few steps.

Any AI agent

This skill is plain instructions — it works with any assistant that accepts custom instructions or system prompts.

Copy the skill content with the button below.
Paste it into your agent's instruction file or system prompt (for example AGENTS.md, .cursorrules, or a custom instructions field).
Ask the agent to apply the skill whenever the task matches.

Claude Code & Claude apps

Claude loads skills automatically from its skills directory.

Claude Code

Create a skill folder — personal: ~/.claude/skills/text-to-cad/, or per-project: .claude/skills/text-to-cad/
Save the skill content as SKILL.md inside that folder.
Claude Code picks it up automatically and invokes it when relevant.

mkdir -p ~/.claude/skills/text-to-cad

Claude.ai / Claude Desktop

Enable Skills under Settings → Capabilities, then upload the skill (a folder or zip containing SKILL.md).

One-prompt install

Paste this prompt into any agent with web access and it will install the skill for you.

Install the "CAD" skill from Onei AI. Fetch https://onei.ai/skills/text-to-cad, extract the full skill content from the page, and save it where you load skills from (for Claude Code: .claude/skills/text-to-cad/SKILL.md). From now on, apply this skill whenever it is relevant to my request.

Skill Content

Markdown Content

Copy this content and use it with your preferred AI agent

---
name: cad
description: Create, modify, inspect, and validate STEP-first parametric CAD parts and assemblies. Use for natural-language CAD specs, reference images, 2D technical drawings, STEP/STP generation or direct inspection, Python CAD source, source-level joints, selector references, geometry facts, measurements, mating deltas, snapshots, and secondary STL/3MF/native GLB outputs from CAD geometry.
---

# CAD generation, inspection, and validation

Provenance: maintained in earthtojake/text-to-cad.
Use the installed local skill files as the runtime source of truth; the
repository link is only for provenance and release review.

## Purpose

Create or modify parametric CAD models from natural-language requirements, generate validated STEP/STP artifacts, inspect geometry references, and return checked outputs. Treat STEP as the primary CAD artifact. Treat STL, 3MF, and native GLB as secondary export workflows that branch from a STEP-first process.

## Use this skill when

Use this skill when the user asks for CAD files, STEP/STP files, build123d source, mechanical parts, assemblies, enclosures, brackets, fixtures, holes, counterbores, countersinks, slots, pockets, bosses, standoffs, ribs, fillets, chamfers, shells, source-level joints, mating, or measurements. Also use it when the user supplies reference images or 2D technical drawings of a part to reproduce or take design intent from.

## Default assumptions

- Units: millimeters.
- Base plane: XY; up/extrusion axis positive Z.
- Output geometry: closed, positive-volume solids unless surfaces or construction geometry are requested.
- Small plastic enclosure wall: 2.0-3.0 mm when unspecified.
- Cosmetic fillet: 1.0-3.0 mm when safe for local geometry.
- M3/M4/M5 normal clearance holes: 3.4/4.5/5.5 mm unless another standard is requested.

## Required workflow

1. Classify the task (new part, new assembly, source modification, direct inspection, measurement/alignment check, snapshot review, secondary output).
2. Write a natural-language CAD brief capturing dimensions, units, feature intent, and validation targets.
3. Check named purchasable components against a parts library before creating placeholder geometry.
4. Plan parameters, intent labels, and datums before editing.
5. Edit source (build123d Python), not generated artifacts; generate STEP via `scripts/step`.
6. Validate geometrically with `scripts/inspect refs --facts --planes --positioning`, then targeted measure/align/frame/diff checks.
7. Snapshot the primary STEP output with `scripts/snapshot` and review it — this step is mandatory, not optional.
8. Repair and rerun the smallest responsible section if a check fails.

## Non-negotiables

- STEP is the primary validated artifact; STL/3MF/GLB are secondary derived exports.
- Use named parameters, closed solids, and source-controlled geometry intent.
- Do not use file-size or git diff churn to compare large CAD artifacts — compare source and inspection output instead.
- Report only checks that actually ran.

Description

This skill lets Claude Code or Codex act as a CAD engineer: describe a part or assembly in plain language, or hand it a reference photo or 2D technical drawing, and it produces a parametric build123d Python source file plus a validated STEP artifact, the standard interchange format for mechanical CAD.

It treats STEP as the primary output and STL, 3MF, and native GLB as secondary exports generated from the same source, which keeps a single source of truth instead of drifting copies. For assemblies, it uses source-level joints and named mating datums so parts click together the way a human CAD engineer would model them, and it applies sane defaults for common mechanical features, wall thickness, fillet radii, and clearance-hole sizing, so it doesn't ask for specifications a competent engineer would assume.

Every generated or modified model goes through a mandatory geometric validation pass, inspecting reference selectors, planes, and positioning, then a rendered snapshot review, before the skill considers the work done. It's part of a broader open-source collection of CAD, robotics, and hardware-design agent skills (text-to-cad), aimed at hardware and product engineers who want an agent that can produce a printable bracket, enclosure, or fixture without hand-authoring CAD source line by line.