U

urdf

by @earthtojakev
4.5(120)

This skill generates and validates URDF robot description files, ensuring the accuracy of robot kinematic models, joints, geometry, units, and inertial data. It automates the generation process, helping developers efficiently create, edit, and debug robot models, avoiding errors from manual XML writing, and ensuring seamless integration with tools like CAD viewers, thereby improving the efficiency and quality of robot development.

urdfroboticscadkinematicsvalidationGitHub
Installation
npx skills add https://github.com/earthtojake/text-to-cad --skill urdf
compare_arrows

Before / After Comparison

1 组
Before

Before this skill, developers manually writing URDF XML files often faced low development efficiency due to errors in frame placement, joint axes, unit inconsistency, or inertial data, leading to high error rates and difficult maintenance.

After

This skill automates URDF generation and includes built-in validation, significantly reducing manual errors, ensuring model consistency and accuracy, and greatly improving the efficiency of robot model development and debugging.

SKILL.md

URDF

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 URDF robot-description outputs. Treat URDF work as constrained kinematic modeling, not just XML writing. The main correctness risks are frame placement, joint-axis semantics, unit consistency, mesh scale, inertial data, and generated-artifact drift.

Core Rules

  1. Treat the Python source that defines gen_urdf() as the source of truth. Treat configured .urdf files as generated artifacts.
  2. Generate only explicit URDF targets. Do not regenerate unrelated CAD, mesh, render, SRDF, SDF, or simulator artifacts from this skill.
  3. The scripts/urdf generator validates generated URDFs by default. Do not use or document a separate validate command.
  4. Before writing or changing URDF XML, establish the robot's frame, joint, geometry, unit, and assumption ledger. See references/design-ledger.md.
  5. Use URDF frame semantics exactly. Joint origins, link frames, joint axes, and visual/collision/inertial origins use different reference frames. See references/frame-semantics.md.
  6. Do not infer spatial transforms, mesh units, handedness, axes, or joint signs from vague prose. Use CAD transforms, dimensioned drawings, measured values, existing source data, or explicit documented assumptions.
  7. Prefer simple, auditable generator code over clever XML construction. Keep constants named by physical meaning, not by arbitrary numbers.
  8. For physical links, model inertial, visual, and collision separately when the target consumer needs them. Frame-only links may intentionally omit mass and geometry.

CAD Viewer Handoff

After completing URDF work that creates or modifies a .urdf, you must ALWAYS hand the explicit file path to $cad-viewer when that skill is installed. $cad-viewer must start CAD Viewer if it is not already running and return link(s) to the relevant created or updated file(s); if $cad-viewer is unavailable or startup fails, report that instead of silently omitting the handoff.

Workflow

  1. Identify the gen_urdf() Python source and target .urdf output.
  2. Identify target consumers: RViz, robot_state_publisher, Gazebo/Ignition, MoveIt, a real robot driver, or another simulator.
  3. Read or create the design ledger before editing frames, origins, axes, mesh scale, limits, or inertials.
  4. Edit the generator source, not generated URDF XML.
  5. Regenerate only explicit targets with scripts/urdf.
  6. Let generation-time validation fail fast on XML, graph, joint, geometry, mesh-reference, and inertial problems.
  7. When geometry or mesh references depend on changed CAD or exported mesh outputs, regenerate those explicit artifacts with the owning CAD or mesh workflow, then regenerate the affected URDF target.
  8. When available, run a consumer smoke test appropriate to the target: RViz display, robot_state_publisher tree, Gazebo/Ignition loading, or MoveIt model loading.
  9. Report remaining assumptions, unchecked spatial data, and validation/smoke-test gaps.

Commands

Run with the Python environment for the project or workspace. Treat python in examples as an interpreter placeholder; if bare python is unavailable, substitute python3, a project virtualenv interpreter, or the configured interpreter path. The URDF generator and lightweight validator use only the Python standard library; downstream consumers such as RViz, Gazebo, or MoveIt may need their own runtime packages.

From this skill directory, the launcher shape is:

python scripts/urdf path/to/source.py
python scripts/urdf path/to/source.py -o path/to/robot.urdf
python scripts/urdf path/to/a.py=out/a.urdf path/to/b.py=out/b.urdf

Plain Python targets write a sibling .urdf beside the source. -o/--output is valid only with one plain target. Use SOURCE.py=OUTPUT.urdf pairs for custom multi-target destinations.

Relative source targets and CLI output overrides are resolved from the current working directory. When running from outside this skill directory, prefix the launcher path so target files still resolve from the intended workspace.

The launcher executes only gen_urdf() and validates the generated URDF output. It does not provide a separate validation-only command.

References

  • Design ledger: references/design-ledger.md
  • Frame semantics: references/frame-semantics.md
  • URDF generator contract: references/generator-contract.md
  • URDF generation command: references/gen-urdf.md
  • URDF edit workflow: references/urdf-workflow.md
  • Generation-time validation expectations: references/validation.md

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs10.4K
Rating4.5 / 5.0
Version
Updated2026年10月24日
Comparisons1

User Rating

4.5(120)
5
37%
4
43%
3
13%
2
5%
1
2%

Rate this Skill

0.0

Compatible Platforms

🤖claude-code

Timeline

Created2026年6月9日
Last Updated2026年10月24日
🎁 Agent Knowledge Cards
Survey