I've been working on this one for a while, with a number of contributions from teammates! It's not the flashiest feature, but it's important to be thinking about maintainability of plugin/skill ecosystems, particularly for large-scale software engineering. Hopefully this helps!
New in Claude Code: claude plugin eval
See what value your plugin is adding, or if it needs more work.
You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences.