Audit a codebase for LLM calls that are really classifications in disguise, then produce a costed swap plan for a System One model. Use when asked to cut AI inference cost or latency, when scoping a performance engagement for a client, when reviewing an agent loop that feels slow, or when asked "where could we use Jev here".
安装
npx skills add OneWave-AI/claude-skills --skill jev-auditnpx skills add OneWave-AI/claude-skills --skill jev-audit -a claude-code -gnpx skills add OneWave-AI/claude-skills --skill jev-audit -a codex -ggemini skills install https://github.com/OneWave-AI/claude-skills.git --path jev-auditgh skill install OneWave-AI/claude-skills jev-auditgit clone --depth 1 https://github.com/OneWave-AI/claude-skills /tmp/OneWave-AI__claude-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/OneWave-AI__claude-skills/jev-audit ~/.claude/skills/jev-audit # Claude Code
cp -R /tmp/OneWave-AI__claude-skills/jev-audit ~/.agents/skills/jev-audit # Codex, Cursor, Gemini CLI, Copilot, OpenCode