DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools…
Install
npx skills add confident-ai/deepeval --skill deepevalnpx skills add confident-ai/deepeval --skill deepeval -a claude-code -gnpx skills add confident-ai/deepeval --skill deepeval -a codex -ggemini skills install https://github.com/confident-ai/deepeval.git --path skills/deepevalgh skill install confident-ai/deepeval deepevalgit clone --depth 1 https://github.com/confident-ai/deepeval /tmp/confident-ai__deepeval
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/confident-ai__deepeval/skills/deepeval ~/.claude/skills/deepeval # Claude Code
cp -R /tmp/confident-ai__deepeval/skills/deepeval ~/.agents/skills/deepeval # Codex, Cursor, Gemini CLI, Copilot, OpenCode