Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
Install
npx skills add NeoLabHQ/context-engineering-kit --skill do-in-stepsnpx skills add NeoLabHQ/context-engineering-kit --skill do-in-steps -a claude-code -gnpx skills add NeoLabHQ/context-engineering-kit --skill do-in-steps -a codex -ggemini skills install https://github.com/NeoLabHQ/context-engineering-kit.git --path skills/do-in-stepsgh skill install NeoLabHQ/context-engineering-kit do-in-stepsgit 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/skills/do-in-steps ~/.claude/skills/do-in-steps # Claude Code
cp -R /tmp/NeoLabHQ__context-engineering-kit/skills/do-in-steps ~/.agents/skills/do-in-steps # Codex, Cursor, Gemini CLI, Copilot, OpenCode