skillarena

Explore documented capabilities and connections for skillarena.

CLI

What your agent can do

Benchmark AI coding agent skills, plugins and CLAUDE.md files: run Claude Code, Codex or OpenCode with and without them and measure pass rate, cost, false "done" claims and test tampering. Works with any LLM.
Via CLI.

Tasks depend on the interface and permissions.

Choose a route that fits your agent.

For agents with a terminal

CLI connection

CLI package

skillarena