Design & Frontend

CAD (text-to-cad's CAD skill)

Give your AI agent the ability to create and edit parametric CAD models from plain language or images, exporting STEP/STL/3MF/GLB files.

55/ 100
Use with care

Useful, but reliability, evidence or controls still have material gaps.

See how it was scored ↓
Works as-is in
Codex · Claude Code · ChatGPT(Partial support) · Claude.ai(Partial support)
Stars
★ 19k
Last updated
1d ago
License
MIT
cadstepstl3mf
+4glbbuild123dmechanical-engineeringopen-cascade

What does this skill do, and when should you use it?

The CAD skill is one of 13 skills in the earthtojake/text-to-cad repository, covering 3D modeling of mechanical parts and assemblies. It instructs the agent to write decorated Python model scripts (build123d-based) that a pinned cadgen CLI builds locally into STEP, with maintainable STL, 3MF and GLB mesh outputs. The workflow also covers project organization, resolving geometry references from prompts, measuring and validating geometry, reviewing snapshots of its own work, and opening existing STEP/STP, STL, 3MF and GLB files in a local CAD Viewer. The repository is MIT-licensed and runs everything through uv, downloading its runtime on first use.

  • Reads/edits decorated build123d Python model scripts and runs python <model>.py to regenerate STEP outputs
  • Exports meshes via @stl/@threemf/@glb decorators or one-off cadgen stl/3mf/glb build commands
  • Resolves prompt references like /path/assembly.step#o1.2.f7 with read_scene + scene.resolve() and measures properties such as face area
  • Writes Python geometry checks for dimensions, clearances and topology, and renders snapshots via cadgen step snapshot for self-review
  • Shows models to the user with cad_show or a local CAD Viewer started with cadgen viewer --detach
  • Diagnoses install/kernel issues with cadgen doctor and explains unexpected rebuilds with cadgen store why
Good fit
  • A mechanical engineer asks the agent to produce a parametric STEP bracket from a verbal description or an annotated image
  • A robotics team organizes a multi-model CAD project (src/ layout, model catalog, formatted output folders) and maintains assemblies
  • A 3D printing user one-off exports an existing STEP part to STL or 3MF
  • An agent receives a CAD Viewer Quick Edit note (file path, references and a marked-up sketch) and edits the corresponding geometry
  • A reviewer verifies dimensions and clearances via snapshots and geometry checks before handing off to the user
Not a fit
  • Users needing 2D DXF drawings — SKILL.md explicitly defers these to the $dxf skill
  • Users needing URDF/SRDF/SDF robot description files — the skill requires the corresponding robot-description skills
  • Offline-restricted environments without uv — the first run must download the runtime and a headless browser

How do you install this skill?

Before you use it
  • Static review only; no commands were executed. All capability claims rest on documentation.
  • cadgen sends anonymous usage stats and crash reports (PostHog) by default; run `uvx cadgen telemetry off` or set CADGEN_TELEMETRY=0 if unwanted.
  • The CAD Viewer local server is unauthenticated (loopback only); do not bind a non-127.0.0.1 host or expose it beyond the local machine.
  • First run downloads runtime and a headless browser from the internet; in mainland-China networks uv/PyPI/browser downloads may be unreachable or slow, with no mirror guidance provided.
  • No Chinese-language support; Windows 11 Smart App Control blocks the unsigned OCP native module — disable it or use WSL.
  • Publisher is unverified; the repository contains 13 skills and this score covers only skills/cad/SKILL.md.
Before you start
Your agent needs
  • Shell / CLI
  • Network access
  • Local filesystem
Install first
  • uv / uvx
  • Python 3.13 (uv-managed)
  • cadgen 0.7.20 (pinned via uvx)

This skill ships with the text-to-cad collection (13 skills; this one lives at skills/cad/SKILL.md). uv must be installed first.

Claude Code

claude plugin marketplace add earthtojake/text-to-cad#latest
claude plugin install text-to-cad@earthtojake

Cursor

git clone --depth 1 --branch latest https://github.com/earthtojake/text-to-cad ~/.cursor/plugins/local/text-to-cad

Grok Build

grok plugin install earthtojake/text-to-cad@latest --trust
grok plugin enable text-to-cad

Gemini

gemini extensions install https://github.com/earthtojake/text-to-cad --ref latest --consent --auto-update

Other agents (Skills CLI)

npx skills add earthtojake/text-to-cad#latest

Claude Desktop has no skill-install command; only the MCP server config (cadgen mcp, pinned cadgen==0.7.20) is documented, added manually to the app config, then restart.

How do you use this skill?

Try saying

Once installed, send your agent any of these to trigger it:

  • Create a 40mm wide, 20mm deep, 6mm thick bracket and export it as STEP and STL
  • Export the assembly in /work/robot/STEP/assembly.step to GLB so I can view it in the browser
  • Here are the dimensions from this sketch — build a parametric model and state your assumptions
  • Open the viewer and show me the bracket.step you just generated, then check the hole spacing against the drawing

Trigger it by describing a modeling task; the skill routes to task-specific reference docs. The core flow: find or create a decorated Python model script (e.g. src/bracket.py with @step(out="../STEP/bracket.step")), edit and run:

python src/bracket.py

Both python and cadgen are pinned uvx invocations (--python 3.13 --from cadgen==0.7.20). One-off mesh exports:

cadgen stl build STEP/bracket.step STL/bracket.stl
cadgen 3mf build STEP/bracket.step 3MF/bracket.3mf
cadgen glb build STEP/bracket.step GLB/bracket.glb

Geometry checks are hand-written Python (no inspect CLI; exploratory checks in tmp/, reusable ones in checks/). After creating or changing geometry you must render and personally read at least one snapshot:

cadgen step snapshot STEP/bracket.step tmp/review.png

Show results with the cad_show tool if available; otherwise run cadgen viewer --host 127.0.0.1 -- --detach (always pass --detach), read url from the JSON line, and return url?file=<URL-encoded absolute path> per file. Assemblies call child models and place results with .moved() or Location * shape; search $step-parts for named purchasable parts before making placeholders.

What are this skill's strengths and limitations?

Pros
  • Fully local workflow — model files never leave the machine; MIT license
  • STEP-first output with maintainable STL/3MF/GLB exports covering mainstream downstream uses
  • Complete documented workflow: modeling, project layout, reference resolution, validation, snapshot review, viewer handoff, repair loop
  • uv-pinned cadgen==0.7.20 and Python 3.13, with cadgen doctor for environment diagnostics
Limitations
  • Hard dependency on uv and a first-run network download (runtime plus a headless browser) — not viable offline on first use
  • The collection sends usage stats and crash reports by default (opt-out available), plus a daily version-check request
  • On Windows 11 with Smart App Control enabled, every cadgen command fails due to the unsigned OCP native module; requires disabling it or using WSL
  • The skill prescribes process, not correctness — geometry accuracy depends on the model code, and snapshot/validation review is performed by the agent itself with no independent guarantee

How does this skill compare with similar options?

Side by side with related skills; every score comes from the same FSRS standard.

Skill FS score Stars Last updated License
CAD (text-to-cad's CAD skill) this page 55 · Use with care ★ 19k 1d ago MIT
DfAM Check — 3D Printability Analysis 67 · Recommended ★ 19k 1d ago MIT
3D Morph PPT Skill 48 · Use with care ★ 32k 5d ago Apache-2.0
Academic Figure Prompt — Modern ML Airy Style 68 · Recommended ★ 2.6k 6mo ago MIT
Banana Claude — Gemini Image Creative Director 59 · Recommended ★ 1.1k 1mo ago MIT

The README positions this skill within a 13-skill library: it complements step.parts (off-the-shelf STEP parts), DXF (2D drawings), URDF/SRDF/SDF (robot descriptions) and manufacturing skills like DfM/SendCutSend/G-code; this skill owns 3D parametric modeling and export itself. The source names no third-party competitors.

How did FollowSkills review this skill?

FollowSkills review · FSRS-2.0
Use with care
55/ 100 5-point scale 2.8 / 5
1Trust14 / 25 · 2.8/5

Evidence: the skill operates purely on local files; no credential access, covert exfiltration or destructive defaults; versions pinned (cadgen==0.7.20, uv --no-config); telemetry on by default but fully disclosed with opt-out (README); viewer binds loopback and SECURITY.md explicitly states the unauthenticated trust boundary. Deductions: telemetry sends by default, local viewer is unauthenticated, first run downloads runtime and a headless browser from the internet, publisher identity unverified, rollback/recovery only partly described. Not full marks.

2Reliability10 / 20 · 2.5/5

Documentation is highly self-consistent: explicit command contracts, doctor diagnostics, migration guides, and well-designed failure feedback (teaching errors, named refusals). Deductions: static review cap of 10; key paths (cadgen build/snapshot/viewer) have no executed reproduction evidence; test suite not present in this evidence.

3Adaptability8 / 15 · 2.7/5

The task table clearly covers modeling/export/inspection/animation/migration, and boundaries are thoroughly declared (closed-loop linkages out of scope, mesh-only limits, etc.). Deductions: core function depends on uv/PyPI downloads, ffmpeg and network first-run, with no statement on mainland-China reachability; no Chinese-language support; semantic trigger precision is only weakly evidenced.

4Convention12 / 15 · 4.0/5

Layered docs (SKILL.md plus references) with progressive disclosure, migration guides, MIT license, version pinning and doctor checks are all strong. Deductions: no standalone changelog/version history for the skill itself, maintenance responsibility only implied via the repository README, unverified publisher, and several referenced reference files are absent from this evidence.

5Effectiveness7 / 15 · 2.3/5

Goals, methods and alternatives (script vs step build, snapshot vs viewer) are clearly argued; outputs are directly usable STEP/STL/3MF/GLB with mandatory self-review snapshots. Deductions: static review cap of 7; no executed representative output verifies direct usability; all benefit claims come from documentation only.

6Verifiability4 / 10 · 2.0/5

README shows CI test and PyPI version badges and links external migration docs — auditable primary material. Deductions: static review cap of 5; this evidence contains no actual test files or third-party execution results for the skill's key paths, and cross-source corroboration is thin.

1 2 3 4 5 6

Open a dimension to read why it scored that way

Reviewed Oct 10, 2026 Reviewed revision b48ff49e0096 Review evidence[1][2][3][4][5][6][7][8][9][10][11][12]

Evidence confidence:Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.

See the full review method →

FAQ

Does it upload my CAD files to the cloud?
No. Modeling and export run locally. Default telemetry sends only usage stats and crash reports tagged with a random ID, explicitly never file names, paths, contents or prompts; disable with uvx cadgen telemetry off, the app menu, or DO_NOT_TRACK=1.
What does one install give me?
text-to-cad is a monorepo with 13 skills. This profile covers only skills/cad/SKILL.md; 2D DXF, robot descriptions and manufacturing checks are separate skills whose capabilities should not be attributed here.
What are the prerequisites?
uv must be installed; cadgen and python run through uvx with fixed arguments (Python 3.13, cadgen==0.7.20). The first run downloads the runtime and a headless browser for snapshots. On Windows 11, watch for Smart App Control blocking the unsigned OCP module.
How do I debug an export failure?
The SKILL.md includes a repair loop: read the error and check the relevant model/geometry/command contract docs, run cadgen doctor to verify the install and CAD kernel load, use cadgen store why <model>.py to explain unexpected rebuilds, and cadgen daemon status for build progress.

More skills from this repository

All from earthtojake/text-to-cad

Dev & Engineering

Engineering Drawing (Text-to-CAD)

Turn a 3D part into a dimensioned engineering-drawing PDF — orthographic views, hidden lines, hole callouts and a title block, all projected from the geometry so the drawing follows the model.

★ 19k FS 59 Recommended 1d ago
Dev & Engineering

G-code Slicing Skill (text-to-cad)

Give your agent the power to slice STL, 3MF and OBJ models into printer-ready G-code with OrcaSlicer, using your own printer presets.

★ 19k FS 60 Recommended 1d ago
Dev & Engineering

DXF Generation & Validation Skill

Generate, regenerate, and validate 2D DXF drawings from Python build123d sources or CAD geometry, ready for laser, plasma, and waterjet cutting.

★ 19k FS 57 Use with care 1d ago
Dev & Engineering

SendCutSend Upload Preflight

Reviews DXF and STEP files against SendCutSend's official ordering guide and catalog before upload, so an agent can catch manufacturability problems before you pay for a prototype.

★ 19k FS 57 Use with care 1d ago
Dev & Engineering

step.parts Catalog Skill

Give your agent the ability to search the step.parts hosted catalog and download real off-the-shelf STEP parts — screws, bearings, motors, servos — instead of sketching crude placeholder geometry.

★ 19k FS 55 Use with care 1d ago
Design & Frontend

DfAM Check — 3D Printability Analysis

Measure mesh files against Design for Additive Manufacturing rules per process (FDM, SLS, SLA/DLP, metal PBF, MJF) and report evidence-backed printability findings before slicing or printing.

★ 19k FS 67 Recommended 1d ago
Dev & Engineering

Bambu Labs Print Handoff Skill

Hand sliced G-code or unsliced models to Bambu Lab printers safely via the official Bambu Connect app or Bambu Studio — the agent never controls the printer.

★ 19k FS 60 Recommended 1d ago
Dev & Engineering

DFM Review Skill

Gives your AI agent a process-specific design-for-manufacturing review for sheet metal, CNC machining or injection molding, with measured evidence and cited rules behind every finding.

★ 19k FS 61 Recommended 1d ago
Dev & Engineering

URDF Robot Description Skill

Give your agent disciplined authoring and validation for URDF robot description files — frames, joints and inertials computed, never guessed.

★ 19k FS 57 Use with care 1d ago
Dev & Engineering

SRDF Skill: MoveIt Planning Semantics

Author and validate MoveIt SRDF planning semantics on top of an existing URDF, so agents stop handing MoveIt wrong planning groups and unsafe collision rules.

★ 19k FS 62 Recommended 1d ago
Dev & Engineering

text-to-cad SDF Skill

Lets your agent author, validate, and visually review SDFormat robot models and worlds, handing them off cleanly to simulators like Gazebo.

★ 19k FS 55 Use with care 1d ago

Related skills