Need to search OpenRouter's 300+ models without leaving your terminal? This gives you live data on pricing, context windows, throughput limits, and per-provider performance metrics like latency and uptime. The decision tree is smart: it routes vague requests like "use the nano banana 2.0 model" through fuzzy matching before you waste time on the wrong model ID. The provider endpoint script is the standout here, showing you which backend is actually fastest for Claude or GPT-4o right now, with p50/p99 breakdowns. Useful if you're comparison shopping models or trying to squeeze better performance out of OpenRouter by picking the right provider.
npx -y skills add openrouterteam/skills --skill openrouter-models --agent claude-codeInstalls to .claude/skills
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills