After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.
Install
npx skills add GarethManning/education-agent-skills --skill ai-claim-checkernpx skills add GarethManning/education-agent-skills --skill ai-claim-checker -a claude-code -gnpx skills add GarethManning/education-agent-skills --skill ai-claim-checker -a codex -ggemini skills install https://github.com/GarethManning/education-agent-skills.git --path skills/student-learning/ai-claim-checkergh skill install GarethManning/education-agent-skills ai-claim-checkergit clone --depth 1 https://github.com/GarethManning/education-agent-skills /tmp/GarethManning__education-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/GarethManning__education-agent-skills/skills/student-learning/ai-claim-checker ~/.claude/skills/ai-claim-checker # Claude Code
cp -R /tmp/GarethManning__education-agent-skills/skills/student-learning/ai-claim-checker ~/.agents/skills/ai-claim-checker # Codex, Cursor, Gemini CLI, Copilot, OpenCode