Railway's official agent skill: create projects, provision databases and buckets, deploy, manage variables and domains, and read build failures back — from the CLI, API or MCP server.
CADSkill
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.
Skill Content
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.
Related Skills
Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
Google's official skill for the gws CLI — drive Gmail, Drive, Calendar, Sheets, Docs, Chat and Admin APIs from an agent, with Model Armor screening.
Netlify's official skill for zero-config managed Postgres — querying from Functions, Drizzle setup, migrations and per-preview database branches.