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.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/davila7/claude-code-templates/main/cli-tool/components/skills/ai-research/safety-alignment-constitutional-ai/SKILL.mdRegistry
github (via claudemarketplaces.com)