Skill Claude Code
Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.
Use cultivar to test your Agent Skills and Docs by running them in sandboxes, and across different agents.
This repository also configures its own agents. See what cultivar tells them →
Skill Claude Code
Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.
Skill Claude CodeCodex
Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.
Skill Claude CodeCodex
Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.