Claude Code Plugin Eval
By Steven Van ·
Creators can write test cases, score a plugin or skill's runs, and compare results with and without it enabled.
Claude Code now includes a plugin eval workflow: create test cases, run a plugin or skill against them, and score the results. The same test cases can then be run with and without the plugin enabled, so a creator can see how much value it actually adds.
Claude Code
Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.
View Claude Code →