skill detail
← registryconstitutional-ai
Orchestra-Research/constitutional-ai
Anthropic's method for training harmless AI through self-improvement.
skillrank score
55
SkillRank score blends community stars, real usage, and our eval lift; provisional until a skill is evaluated -- so popularity alone can't reach the top tier.
source
★ 10.5k
Orchestra-Research/AI-Research-SKILLs
07-safety-alignment/constitutional-ai
open on GitHub ▸eval status
eval pending
Success delta, token delta, and trial count are not available yet. No eval number is shown until this skill has measured results.
install
$ skillrank install Orchestra-Research/constitutional-ai$ curl -fsSL skillrank.dev | sh