Makes data code correct first and cheap second: pins down the output, estimates sizes before running, checks schema and join contracts, chooses the engine, reads the query plan before tuning, and has results returned or published as artifacts instead of printed. Covers synthetic data and tests for data code. Hands back the changed code with the measurement behind every speed or memory claim.
Install
npx skills add rhawk117/rygentic-harness --skill data-engineeringnpx skills add rhawk117/rygentic-harness --skill data-engineering -a claude-code -gnpx skills add rhawk117/rygentic-harness --skill data-engineering -a codex -ggemini skills install https://github.com/rhawk117/rygentic-harness.git --path plugins/python-harness/skills/data-engineeringgh skill install rhawk117/rygentic-harness data-engineeringgit clone --depth 1 https://github.com/rhawk117/rygentic-harness /tmp/rhawk117__rygentic-harness
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/rhawk117__rygentic-harness/plugins/python-harness/skills/data-engineering ~/.claude/skills/data-engineering # Claude Code
cp -R /tmp/rhawk117__rygentic-harness/plugins/python-harness/skills/data-engineering ~/.agents/skills/data-engineering # Codex, Cursor, Gemini CLI, Copilot, OpenCode