Skill

constitutional-ai

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.

Bundled with Research Agent Skills. Its trust score, security findings and other files are on the plugin page.

SKILL.md

Path: skills/constitutional-ai/SKILL.md
Size: 9.8 KB
SHA-256: 5b13cc8dcbc2702e6cc3cc13b8d06b22b81da9d51cca870837f8a0b7c93443a4

View source on GitHub
All skills in this plugin

Install

Install the plugin's skills with the Skills CLI:

npx [email protected] add KalarisLabs/research-agent-skills