Run AgentV evaluations and optimize agents through eval-driven iteration. Triggers: run evals, benchmark agents, optimize prompts/skills against evals, compare agent outputs across providers, analyze eval results, offline evaluation of recorded sessions, run autoresearch, optimize unattended, run overnight optimization loop. Not for: writing/editing eval YAML without running (use agentv-eval-writer), analyzing existing traces/JSONL without re-running (use agentv-trace-analyst).
$npx -y skills add entityprocess/agentv --skill agentv-benchInstalls into the current project.
Run `npx skills use "https://github.com/entityprocess/agentv" --skill "entityprocess/agentv/agentv-bench"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/entityprocess/agentv" that are relevant to the current task. Run `npx skills add "https://github.com/entityprocess/agentv"` and select the relevant skills, then follow their instructions.