sdf — Claude Code skill: what it does, how to install
This skill authors and validates SDFormat files for models and worlds, then helps prepare them for simulator handoff.
npx skills add earthtojake/text-to-cad --skill sdf -a claude-codeWhat sdf does
The skill works with .sdf and SDFormat XML for models, worlds, links, joints, poses, frames, inertials, visual and collision geometry, sensors, lights, physics, plugins, and included resources. It edits the XML directly, with the SDF file as the source of truth.
Validation uses cadgen sdf validate, with strict mode, JSON output, and snapshots available through cadgen sdf snapshot. The validator checks document shape, name scopes, pose and frame graphs, geometry, mesh URIs, inertials, sensors, and plugins. The commands use uvx with Python 3.13 and cadgen==0.7.26.
This skill targets SDFormat, not signed-distance-field geometry. That distinction matters before installation. When a URDF already exists, the guidance is to derive SDF from it instead of authoring the geometry again.
What it helps with
- author an SDF model for a robot or object
- define a simulator world for Gazebo
- check poses, frames, and joints
- catch invalid mesh URIs or geometry
- prepare an SDF file for simulator handoff
Example prompts for the agent
- Create a model in `path/to/model.sdf` and validate it with `cadgen sdf validate`.
- Validate `path/to/model.sdf` in strict mode and print the result as JSON.
- Create a snapshot of `path/to/model.sdf` at `review.png` for a placement review.
How to install sdf
1Skills CLI (Vercel)
npx skills add earthtojake/text-to-cad --skill sdf -a claude-code2Manually: put the files in place
~/.claude/skills/sdf/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/sdf/
1Skills CLI (Vercel)
npx skills add earthtojake/text-to-cad --skill sdf -a codex2Manually: put the files in place
.agents/skills/sdf/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add earthtojake/text-to-cad --skill sdf -a cursor2Manually: put the files in place
.cursor/skills/sdf/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install earthtojake/text-to-cad sdf2Manually: put the files in place
.github/skills/sdf/SKILL.md1Skills CLI (Vercel)
npx skills add earthtojake/text-to-cad --skill sdf -a gemini-cli2Platform CLI
gemini skills install https://github.com/earthtojake/text-to-cad --path skills/sdfManually: put the files in place
.devin/skills/sdf/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add earthtojake/text-to-cad --skill sdf -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set7
The whole set →Similar
Questions about sdf
How do I install sdf in Claude Code?
Run npx skills add earthtojake/text-to-cad --skill sdf -a claude-code, run the same command again, then open ~/.claude/skills/sdf/SKILL.md.
What does sdf do?
The skill authors and validates SDFormat documents for models and worlds. It also supports checks before simulator handoff.
Is sdf for signed-distance-field geometry?
No. It is for SDFormat and simulator SDF files, not signed-distance-field geometry.
Source text
SKILL.md · MIT
---
name: sdf
description: SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for `.sdf` files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use for signed-distance-field geometry. Open and visually review existing SDF files in CAD Viewer.
license: MIT
---
# SDF
Provenance: maintained in [earthtojake/text-to-cad](https://github.com/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 when the deliverable is an SDFormat document. SDFormat describes simulator and world behavior: models, worlds, frames, poses, links, joints, inertials, visuals, collisions, sensors, lights, physics, plugins, includes, and simulator metadata.
This skill is for **SDFormat**, not signed-distance-field geometry.
The `.sdf` file is the source of truth: author and edit the XML directly. There is no `gen_sdf()` contract.
## Setup
Run cadgen through [uv](https://docs.astral.sh/uv/), so this skill's commands share
one installation, and its warm build daemon, with the CAD app's server:
- `cadgen` below means `uvx --no-config --managed-python --python 3.13 --from cadgen==0.7.26 cadgen`
- `python` below means `uvx --no-config --managed-python --python 3.13 --from cadgen==0.7.26 python`
The first run downloads that installation and the first snapshot its headless
browser; later runs reuse both.
## Core rules
1. Author `.sdf` XML directly and validate every created or modified file with `cadgen sdf validate` before reporting completion.
2. Identify the target consumer before editing: Gazebo/libsdformat version, another simulator, visualization-only tooling, model package, or world handoff.
3. Decide document kind: model-level SDF, world-level SDF, or model-in-world. Prefer model-level SDF for reusable robot/object exports.
4. Use SI units unless the target explicitly requires otherwise: meters, kilograms, seconds, radians.
5. Prefer `version="1.12"` for new outputs unless the target consumer constrains the version.
6. Establish the design ledger before writing poses, frames, joint axes, mesh scales, inertials, sensors, or plugins, and keep it as a comment block at the top of the `.sdf`. Use `references/design-ledger.md` and `references/llm-guardrails.md`.
7. Write `relative_to` / `expressed_in` explicitly on every nontrivial pose and axis. Implicit frame defaults are the top SDF failure mode. See `references/frame-semantics.md`.
8. Do not infer spatial transforms from visual impression alone. Derive poses, axes, scale, mass, inertia, and frame names from upstream source data, drawings, simulator documentation, measured values, or explicit assumptions. Never freehand computed numbers — use formulas or a throwaway helper script (inertia tensors, unit conversions).
9. When the robot already has a URDF, derive the SDF from it instead of re-authoring geometry; see `references/interoperability.md`.
10. Regenerate upstream geometry, mesh, robot-description, render, topology, or package assets with their owning workflows before editing SDF that references them.
11. After authoring, run available checks: bundled validation (which runs `gz sdf --check` itself whenever `gz` is on PATH), simulator load, joint motion, and plugin/sensor startup.
12. Report assumptions, skipped checks, unresolved resource paths, and target-specific compatibility risks.
## Scope
Use this skill for SDFormat outputs. Do not use it for signed-distance-field modeling, raw geometry generation, planning semantics, or to paper over incorrect upstream robot/source data unless the task is explicitly simulator-only.
## Show the model
Show the user each file you create or change, and any they ask to see. Snapshots and
validation don't replace this.
- If your tools include `cad_show` (your host may prefix it), use it with the file's
absolute path, and follow its description for when to call it again. `cad_view` reads
what the user selected; `cad_screenshot` shows you what they see. Neither is a review
of your own work.
- Otherwise run the CAD Viewer, from any folder:
```bash
cadgen viewer --host 127.0.0.1 --json --detach
```
`--detach` returns once the viewer answers requests and leaves it running in the
background: always pass it, since a foreground viewer never exits (and piping its
output through `tail` can hide the URL for good). It starts this machine's one viewer,
or reuses it. Read `url` from its one JSON line (never guess the port), and for each
file return `url?file=<its URL-encoded absolute path>`. If it fails to launch, say so.
Review placement, resources and joints. The viewer does not execute simulator
plugins or validate dynamics; keep simulator checks separate.
## Workflow
1. Locate the target `.sdf` and its consumers.
2. Read or create the design ledger comment block.
3. Read `references/frame-semantics.md` before editing any `<pose>`, `<frame>`, joint axis, `relative_to`, `expressed_in`, nested scope, sensor frame, or plugin frame.
4. Author the XML directly, following the worked examples in `references/examples.md`.
5. Validate the explicit target with `cadgen sdf validate`; treat bundled validation as a guardrail, not simulator proof.
6. Run target-consumer smoke tests when available (`references/smoke-tests.md`).
7. Show the result ([Show the model](#show-the-model)). Static rendering does not execute SDF plugins or read file-authored motion metadata.
8. Report checks run, checks skipped, and assumptions.
## Commands
Run `cadgen` as Setup defines it. `cadgen doctor <skill-dir>` reports the installation in use and checks that it is the one this skill pins — docs drift silently on another. Validation itself needs nothing beyond the Python standard library; only snapshots need the browser. Use `cadgen <verb> --help` for the complete current interface.
```bash
cadgen sdf validate path/to/model.sdf
cadgen sdf validate path/to/model.sdf --strict
cadgen sdf validate path/to/model.sdf --json
cadgen sdf snapshot path/to/model.sdf review.png
```
The validator checks document shape, name scopes, pose/frame graphs, joints, geometry, mesh URIs, inertials, sensors, and plugins, and prints its findings plus a summary. One run validates ONE file: `--strict` treats warnings as failures and `--json` prints one line of `{"ok", "path", "issues": [{"severity", "code", "message", "element", "hint"}], "summary"}`, where `element` is the XML path. It exits nonzero if the target fails.
External checking is on by default:
```bash
cadgen sdf validate path/to/model.sdf --gz-check required
cadgen sdf validate path/to/model.sdf --gz-check never
```
`gz sdf --check` is target-consumer validation. `--gz-check auto` is the default: it runs when `gz` is on PATH, reporting `gz_check_passed` or the tool's own output as the error `gz_check_failed`, and otherwise notes `info: gz_check_unavailable` and carries on. An absent optional tool says nothing about the file, so it never fails a clean document and `--strict` does not change that. `--gz-check required` makes the tool mandatory — a missing `gz` is then an error — and `--gz-check never` skips it outright.
## Required report shape
When finishing an SDF task, include a compact report:
```text
Validated: path/to/model.sdf
Checks run:
- bundled SDF validation: passed
- gz sdf --check: skipped, gz not installed
- simulator load: skipped, target simulator unavailable
- viewer review: live link returned, or explicit launch failure
Assumptions:
- Assumed mesh units are meters.
- Assumed lidar frame is coincident with lidar_link.
Risks:
- Camera plugin filename was not verified in the target simulator environment.
```
## Snapshot Tool
`cadgen sdf snapshot` renders the robot to a PNG still, using the same shared
CLI and headless browser runtime every rendering skill uses — so a snapshot matches what
the CAD Viewer shows.
```bash
cadgen sdf snapshot path/to/robot.sdf review.png
```
It accepts `.sdf` only (a format door, same `TARGET [OUT]` grammar as the rest). Pose the robot with `--joint-values` — `{joint: degrees}` JSON,
joints you do not name staying at their defaults, where the CAD Viewer opens the robot (the
`"jointValues"` job field is the same thing in a packet). The snapshot draws the robot with the
viewer's own scene, so it shows what the viewer shows, and a link mesh that cannot be loaded
fails it rather than leaving the link out. Robots are authored in metres and are framed on the
robot scene scale automatically.
A normal snapshot uses Solid mode and Light appearance. The display mode is `solid`
(the default) or `parts` (each link its own colour), each at its own defaults;
`--grid` draws the measuring grid under the robot, and `--preview` draws Preview's
shared photographic scene instead, in perspective. Inline display JSON and JSON files
are the Viewer's display object: `mode`, `grid`, `appearance` (`light`, the default,
or `dark`), `camera` (projection and focal length) and `clip`.
Top-level `--camera` and `--joint-values` remain active in every display mode.
`display.clip` cuts the robot as the viewer's Clip does
(`{"clip":{"axis":"x","at":0.05}}`, `at` in metres); `exploded`, and `shaded`, `xray`,
`hidden-line` and `wireframe`, describe a STEP model's CAD edges and parts, and are
refused by name here. A Quick Edit job from the viewer replays as it is: its `jointValues`, its
`selection.hide` (the parts hidden in the Links panel, by their ids), its clip and
annotation (`cadgen snapshot --job <file>`). Quick Edit supplies inline JSON or a
`.snapshot.json` path; save inline JSON to a temporary file before using `--job`.
Inspect supplied annotations before editing. Without annotations, the captured
view is optional context; render it when useful to the request.
Link meshes are resolved relative to the description, so they must be present: an
unhydrated Git LFS pointer fails as "No link mesh loaded for robot". Run
`git lfs checkout <mesh dir>` first.
The grammar is `cadgen sdf snapshot TARGET [OUT] [flags]`, the same one every
format door uses. Use `cadgen sdf snapshot --help` for the complete current
interface — the flags a robot cannot act on are absent from it, not refused by it.
## References
- SDF workflow: `references/sdf-workflow.md`
- Worked examples (golden skeletons): `references/examples.md`
- LLM guardrails: `references/llm-guardrails.md`
- Design ledger: `references/design-ledger.md`
- Frame semantics: `references/frame-semantics.md`
- Validation scope: `references/validation.md`
- Smoke tests: `references/smoke-tests.md`
- Interoperability notes (URDF-derived SDF, meshes, Gazebo): `references/interoperability.md`
© earthtojake · MIT · earthtojake/text-to-cad