Decide whether an AI/LLM/agent/retrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the result; then design, gate, judge, and defend it. Not ordinary unit tests.
安装
npx skills add davila7/claude-code-templates --skill eval-geniusnpx skills add davila7/claude-code-templates --skill eval-genius -a claude-code -gnpx skills add davila7/claude-code-templates --skill eval-genius -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/development/eval-geniusgh skill install davila7/claude-code-templates eval-geniusgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/development/eval-genius ~/.claude/skills/eval-genius # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/development/eval-genius ~/.agents/skills/eval-genius # Codex, Cursor, Gemini CLI, Copilot, OpenCode