Gcode logo

Gcode

CommunityPopular
earthtojake
gcode

Generate, inspect, dry-run, and statically validate plain FDM `.gcode` from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice `.stl`, `.obj`, unsliced `.3mf`, `.ply`, `.glb`, or `.gltf` into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate generated G-code before any printer-specific handoff.

Overview

Publisherearthtojake
Repositorytext-to-cad
Skill namegcode
Stars
16K
Forks
1.7K
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Gcode 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.
  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/earthtojake/text-to-cad.git /tmp/text-to-cad
mkdir -p .claude/skills
cp -r /tmp/text-to-cad/skills/gcode .claude/skills/gcode
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gcode 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 Gcode 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 Gcode 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.

G-code

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.

Use this skill for plain .gcode generation from mesh files. It is printer-agnostic and never uploads, starts, or packages print jobs.

Workflow

  1. Confirm the input is a supported mesh: .stl, .obj, unsliced .3mf, .ply, .glb, or .gltf.
  2. Require an explicit printer/profile wrapper JSON. Do not invent real-printer profiles.
  3. Discover slicer backends when the backend is unknown:
bash
python scripts/gcode_tool.py discover
  1. Inspect the input:
bash
python scripts/gcode_tool.py inspect --input path/to/model.stl --json
  1. Dry-run the slicer command before executing:
bash
python scripts/gcode_tool.py slice \
  --input path/to/model.stl \
  --output /tmp/model.gcode \
  --profile path/to/profile.json \
  --backend auto \
  --dry-run
  1. Execute only after the dry-run command and profile are appropriate:
bash
python scripts/gcode_tool.py slice \
  --input path/to/model.stl \
  --output /tmp/model.gcode \
  --profile path/to/profile.json \
  --backend auto \
  --execute
  1. Validate the generated G-code:
bash
python scripts/gcode_tool.py validate \
  --gcode /tmp/model.gcode \
  --profile path/to/profile.json \
  --json

Profile Contract

Every slice requires a wrapper profile JSON with an absolute native slicer profile path:

json
{
  "backend": "orcaslicer",
  "native_config": "/absolute/path/to/native-slicer-profile",
  "machine": {
    "name": "Example Printer",
    "bed_size_mm": [180, 180],
    "z_height_mm": 180,
    "motion_bounds_mm": {
      "x": [0, 180],
      "y": [0, 180],
      "z": [0, 180]
    }
  },
  "filament": {
    "type": "PLA",
    "nozzle_temp_c": 220,
    "bed_temp_c": 65
  }
}

The wrapper supplies validation bounds and backend selection. machine.motion_bounds_mm is optional; omit it for the default 0..bed_size and 0..z_height bounds, or set it from a native printer profile when start/end G-code intentionally uses safe wipe/purge positions outside the printable area. The native slicer profile remains the source of detailed process, printer, and filament behavior.

For OrcaSlicer, use native_settings and native_filaments when the real profile is split across machine, process, and filament JSON files. Keep native_config as an absolute path to the primary native profile for compatibility:

json
{
  "backend": "orcaslicer",
  "native_config": "/absolute/path/to/machine-or-process.json",
  "native_settings": [
    "/absolute/path/to/machine.json",
    "/absolute/path/to/process.json"
  ],
  "native_filaments": [
    "/absolute/path/to/filament.json"
  ],
  "machine": {
    "name": "Example Printer",
    "bed_size_mm": [180, 180],
    "z_height_mm": 180
  },
  "filament": {
    "type": "PLA",
    "nozzle_temp_c": 220,
    "bed_temp_c": 65
  }
}

Backends And Inputs

Preferred slicer backend order is orcaslicer, prusa-slicer, then curaengine. Prefer installing OrcaSlicer when no preferred backend is available; on macOS use brew install --cask orcaslicer and then rerun discover. The helper checks both PATH and the usual /Applications/OrcaSlicer.app cask location. Bambu Studio may be reported by discovery as available but is not preferred because its CLI export path has shown macOS instability.

Pass .stl, .obj, and unsliced .3mf directly to the slicer. Convert .ply, .glb, and .gltf to temporary STL at execution time with optional trimesh; if trimesh is unavailable, ask the user to install it or provide .stl, .obj, or unsliced .3mf.

Reject .step, .stp, .dxf, .svg, .urdf, and .sdf in v1. inspect and slice fail with a structured remediation object naming the skill and command that produce a sliceable mesh; use it instead of inferring a conversion workflow:

  • .step, .stp: boundary-representation CAD, not a mesh. Export an STL sidecar with $cad (cadgen stl build <input.step> <output>.stl — the door takes the STEP document; a model script is refused, run python <model>.py first), then slice the exported .stl here.
  • .dxf, .svg: 2D drawings with no 2D-to-mesh conversion in this toolchain. Model the 3D solid in $cad as a @step model script and export an STL sidecar, then slice that. If the part is a flat cut rather than a print, use $sendcutsend instead of this skill.
  • .urdf, .sdf: robot descriptions that reference per-link mesh files. Slice the referenced .stl/.obj meshes one at a time; regenerate stale or missing ones from the owning CAD source with $cad first. Use $urdf or $sdf for the robot description itself.

Read references/slicer-backends.md when backend behavior, profile expectations, or source links matter.

Validation

Always validate generated G-code before handing it to printer-specific workflows. The validator checks for non-empty content, temperature commands, movement commands, extrusion moves, XYZ bounds, and unknown command warnings.

Read references/gcode-validation.md when interpreting validation output or deciding whether a warning is acceptable.

Bambu Boundary

This skill generates plain .gcode only. It does not create Bambu .gcode.3mf archives and does not contact printers. For Bambu upload/start workflows, hand off the validated plain .gcode to $bambu-labs. Let $bambu-labs choose the printer-specific LAN handoff, such as an A1 Mini template project or an explicitly enabled bambox project package.

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 Gcode AI skill do?

Generate, inspect, dry-run, and statically validate plain FDM `.gcode` from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice `.stl`, `.obj`, unsliced `.3mf`, `.ply`, `.glb`, or `.gltf` into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate generated G-code before any printer-specific handoff.

Why use Gcode on TypingMind?

Because you install it once and use it with any model. Gcode 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 Gcode in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/earthtojake/text-to-cad/tree/main/skills/gcode. 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 Gcode?

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 Gcode?

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

Is the Gcode AI skill free?

Yes. It is published on GitHub by earthtojake 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 👇