Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Install
npx skills add davila7/claude-code-templates --skill constitutional-ainpx skills add davila7/claude-code-templates --skill constitutional-ai -a claude-code -gnpx skills add davila7/claude-code-templates --skill constitutional-ai -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/safety-alignment-constitutional-aigh skill install davila7/claude-code-templates constitutional-aigit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/safety-alignment-constitutional-ai ~/.claude/skills/constitutional-ai # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/safety-alignment-constitutional-ai ~/.agents/skills/constitutional-ai # Codex, Cursor, Gemini CLI, Copilot, OpenCode