Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
安装
npx skills add xberg-io/xberg --skill benchmark-workflownpx skills add xberg-io/xberg --skill benchmark-workflow -a claude-code -gnpx skills add xberg-io/xberg --skill benchmark-workflow -a codex -ggemini skills install https://github.com/xberg-io/xberg.git --path .ai-rulez/skills/benchmark-workflowgh skill install xberg-io/xberg benchmark-workflowgit clone --depth 1 https://github.com/xberg-io/xberg /tmp/xberg-io__xberg
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/xberg-io__xberg/.ai-rulez/skills/benchmark-workflow ~/.claude/skills/benchmark-workflow # Claude Code
cp -R /tmp/xberg-io__xberg/.ai-rulez/skills/benchmark-workflow ~/.agents/skills/benchmark-workflow # Codex, Cursor, Gemini CLI, Copilot, OpenCode