Public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated.
安装
npx skills add lawve-ai/awesome-legal-skills --skill adjudicative-ai-impartiality-challengenpx skills add lawve-ai/awesome-legal-skills --skill adjudicative-ai-impartiality-challenge -a claude-code -gnpx skills add lawve-ai/awesome-legal-skills --skill adjudicative-ai-impartiality-challenge -a codex -ggemini skills install https://github.com/lawve-ai/awesome-legal-skills.git --path skills/adjudicative-ai-impartiality-challenge-adrian-lerergh skill install lawve-ai/awesome-legal-skills adjudicative-ai-impartiality-challengegit clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills /tmp/lawve-ai__awesome-legal-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/lawve-ai__awesome-legal-skills/skills/adjudicative-ai-impartiality-challenge-adrian-lerer ~/.claude/skills/adjudicative-ai-impartiality-challenge # Claude Code
cp -R /tmp/lawve-ai__awesome-legal-skills/skills/adjudicative-ai-impartiality-challenge-adrian-lerer ~/.agents/skills/adjudicative-ai-impartiality-challenge # Codex, Cursor, Gemini CLI, Copilot, OpenCode