Ai Safety Auditor
eddiebe147
Analyzes AI outputs for potential harms like bias, toxicity, or misinformation, flagging risks for review.
Claude Code
vlatest48
Doesn't installBrowse skills
41,264 listings from across the agent ecosystem. None of them have been code-reviewed — check the source before you install.
Looking for what's new? See the repos gaining stars fastest.
3 skills matching “safety”
Listed
Listed
Compliance Anthropic
lawvable
Ensures AI outputs align with Anthropic's safety principles and legal requirements, minimizing risk and promoting responsible use.
Claude Code
vlatest9
Together Evaluations
zainhas
Together Evaluations assesses large language model outputs for quality, safety, and alignment, streamlining evaluation workflows & improving LLM performance.
Claude Code
vlatest7
Can't find what you need?