Evaluate a factor library — recompute Information Coefficient (IC), ICIR, win rate, and turnover on held-out data, and surface train→test decay. Use to judge how good a mined library actually is out of sample. Triggers on "evaluate factors", "compute IC", "how good is this library", "factor metrics", "ICIR", "is this factor overfit", "out-of-sample".
$npx -y skills add minihellboy/factorminer --skill factor-evaluationInstalls into the current project.
Run `npx skills use "https://github.com/minihellboy/factorminer" --skill "minihellboy/factorminer/factor-evaluation"` 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/minihellboy/factorminer" that are relevant to the current task. Run `npx skills add "https://github.com/minihellboy/factorminer"` and select the relevant skills, then follow their instructions.