Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
安装
npx skills add NeoLabHQ/context-engineering-kit --skill agent-evaluationnpx skills add NeoLabHQ/context-engineering-kit --skill agent-evaluation -a claude-code -gnpx skills add NeoLabHQ/context-engineering-kit --skill agent-evaluation -a codex -ggemini skills install https://github.com/NeoLabHQ/context-engineering-kit.git --path plugins/customaize-agent/skills/agent-evaluationgh skill install NeoLabHQ/context-engineering-kit agent-evaluationgit clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit /tmp/NeoLabHQ__context-engineering-kit
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NeoLabHQ__context-engineering-kit/plugins/customaize-agent/skills/agent-evaluation ~/.claude/skills/agent-evaluation # Claude Code
cp -R /tmp/NeoLabHQ__context-engineering-kit/plugins/customaize-agent/skills/agent-evaluation ~/.agents/skills/agent-evaluation # Codex, Cursor, Gemini CLI, Copilot, OpenCode