Skill
constitutional-ai
Published by Orchestra Research
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.
Skill details
- Resource Id
- 3c91817f-3546-4eb4-9b55-0a7cbab237a3
- Skill Md Url
- https://github.com/davila7/claude-code-templates/blob/14680ec431ec8cbfd42b12ddcbe58e2f4ee3cccf/cli-tool/components/skills/ai-research/safety-alignment-constitutional-ai/SKILL.md
- Supported Agents
- Claude Code
- Version
- 1.0.0
- Created At
- "2026-10-08T13:50:31.074Z"
- Updated At
- "2026-10-08T13:50:31.074Z"