Use this skill to run DataHub's saved evals and report answers for judging. Triggers on: "run our evals", "run the eval suite", "run eval urn:li:eval:...", "how are our evals doing", "check for eval regressions", "upload this answer as an eval result", "score this answer with the DataHub judge", "compare two agents on the same eval".
Install
npx skills add datahub-project/datahub-skills --skill datahub-evalsnpx skills add datahub-project/datahub-skills --skill datahub-evals -a claude-code -gnpx skills add datahub-project/datahub-skills --skill datahub-evals -a codex -ggemini skills install https://github.com/datahub-project/datahub-skills.git --path skills/datahub-evalsgh skill install datahub-project/datahub-skills datahub-evalsgit clone --depth 1 https://github.com/datahub-project/datahub-skills /tmp/datahub-project__datahub-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/datahub-project__datahub-skills/skills/datahub-evals ~/.claude/skills/datahub-evals # Claude Code
cp -R /tmp/datahub-project__datahub-skills/skills/datahub-evals ~/.agents/skills/datahub-evals # Codex, Cursor, Gemini CLI, Copilot, OpenCode