sdf
sdf is a skill for creating and modifying SDFormat files through conversational commands. Whether you're designing robot models or building simulation environments, this tool translates your descriptions into valid .sdf geometry and configuration. Perfect for roboticists and simulation engineers who want faster CAD workflows.
sdf generates SDFormat (.sdf) files through conversational commands, translating your robot model descriptions into valid XML geometry and configuration. You describe your robot's structure—links, joints, sensors, and physics properties—and sdf produces simulator-ready files that Gazebo can load directly. This accelerates CAD workflows for roboticists building simulation environments.
AI-generated summary based on this skill's SKILL.md
Install
earthtojake/text-to-cad/sdf · repository language: JavaScript
git clone https://github.com/earthtojake/text-to-cad
cp -r text-to-cad/skills/sdf ~/.claude/skills/sdfFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I create SDF files for Gazebo using sdf?
sdf generates SDFormat (.sdf) files through conversational commands, translating your robot model descriptions into valid XML geometry and configuration. You describe your robot's structure—links, joints, sensors, and physics properties—and sdf produces simulator-ready files that Gazebo can load directly. This accelerates CAD workflows for roboticists building simulation environments.
Can sdf help me write a robot description in SDF format?
Yes. sdf specializes in robot description generation. You provide details about your robot's links, joints, inertial properties, poses, and frames, and sdf constructs the complete SDFormat model file. The skill handles collision geometry, mesh URIs, and frame setup, ensuring your robot description is properly structured for simulation.
How do I validate SDF documents before loading into Gazebo?
sdf includes validation capabilities to ensure your SDFormat documents are compatible with simulators before deployment. The skill checks XML structure, verifies simulator compatibility, and flags configuration errors. This validation step prevents load failures and saves debugging time when handing off SDF models to Gazebo or other simulators.
What can sdf configure in robot joint and link setup?
sdf handles comprehensive robot configuration: links with inertial properties and mass, joints with constraints and dynamics, sensor and light placement, physics parameters, and plugin metadata. You can also set up collision geometry, mesh references, poses, and frames—everything needed to fully describe a robot's kinematic and dynamic structure in SDFormat.
Can I generate .sdf models programmatically with sdf?
sdf is designed for conversational generation of SDFormat files, making it ideal for rapid iteration and CAD-like workflows. While the skill translates your descriptions into valid .sdf output, it focuses on interactive model creation rather than low-level API scripting, making it accessible to simulation engineers who prefer natural language commands over manual XML editing.
What license does sdf use?
sdf is released under the MIT license, making it free to use, modify, and distribute for both commercial and personal projects. The permissive licensing ensures you can integrate sdf into your robotics workflows without legal restrictions.
SKILL.md
rendered from the published skill — quoted content, verbatim
SDF
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 when the deliverable is an SDFormat document or a Python gen_sdf() source. 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.
Core rules
- Treat the Python file defining
gen_sdf()as source of truth. Treat configured.sdffiles as generated artifacts unless the user explicitly asks for direct XML
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 15 files
skills/sdf/LICENSE
skills/sdf/SKILL.md
skills/sdf/agents/openai.yaml
skills/sdf/references/builder-helpers.md
skills/sdf/references/design-ledger.md
skills/sdf/references/examples.md
skills/sdf/references/frame-semantics.md
skills/sdf/references/gen-sdf.md
skills/sdf/references/generator-contract.md
skills/sdf/references/implementation-notes.md
skills/sdf/references/interoperability.md
skills/sdf/references/llm-guardrails.md
skills/sdf/references/sdf-workflow.md
skills/sdf/references/smoke-tests.md
skills/sdf/references/validation.md