A text-to-cad skill let Codex produce a 7-DOF robot arm with kinematics, a GUI and STEP parts in one demo prompt, though not the gripper.
A text-to-cad skill let Codex produce a 7-DOF robot arm with kinematics, a GUI and STEP parts in one demo prompt, though not the gripper.
Jake Fitzgerald installed the open source text-to-cad skill package in Codex, running GPT 5.5. The agent writes build123d Python scripts, regenerates the geometry locally, and outputs STEP parts plus a URDF. In a 22-second demo, one prompt produced a 7-DOF arm with working kinematics and a custom GUI, driven almost entirely by prompting.
The arm's URDF, kinematics, GUI and STEP assembly were all generated, except the gripper. Fitzgerald says similar work would have taken weeks across half a dozen tools. Commenters questioned the joint limits and parts that wouldn't assemble.
The homepage benchmark prompt was an excerpt. Real runs expand a short request into a full spec with GPT 5.5 Pro first, so vague prompts will likely do worse.
Using a text-to-CAD approach with CadQuery, generate a model of [a robot arm / mechanism] with [number of joints, size, and constraints] in [folder]. Include the parts as separate STEP files and a simple viewer so I can inspect it. Finish by listing any parts you could not model well so I can handle them myself.
Plan, execute and review a cross-cutting refactor in small batches, with Claude Code making the edits and GitHub Copilot reviewing each PR.
Claude Code reads your coverage report, picks the riskiest untested modules and writes unit tests that pass, one small PR at a time.
A Claude Code-built agent checked ESPN every 30 minutes and sent each 2026 World Cup final score, written up in a persona, to a 3-person Signal group, with a code check on scores.