The methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction.
安装
npx skills add avelikiy/great_cto --skill quant-validationnpx skills add avelikiy/great_cto --skill quant-validation -a claude-code -gnpx skills add avelikiy/great_cto --skill quant-validation -a codex -ggemini skills install https://github.com/avelikiy/great_cto.git --path skills/quant-validationgh skill install avelikiy/great_cto quant-validationgit clone --depth 1 https://github.com/avelikiy/great_cto /tmp/avelikiy__great_cto
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/avelikiy__great_cto/skills/quant-validation ~/.claude/skills/quant-validation # Claude Code
cp -R /tmp/avelikiy__great_cto/skills/quant-validation ~/.agents/skills/quant-validation # Codex, Cursor, Gemini CLI, Copilot, OpenCode