This covers the two gotchas that trip up most teams moving to Redis Cluster: CROSSSLOT errors when you try multi-key operations across shards, and overloaded primaries when you haven't configured replica reads. The hash tag guidance is practical, showing you how to group related keys with curly braces so transactions and pipelines work, plus when not to do it (tagging everything defeats sharding). The replica read section is short but hits the key point: eventual consistency is fine for dashboards and caches, terrible for anything requiring strict freshness. If you're designing keys for a cluster or debugging why MGET suddenly broke in production, this will save you an hour of Stack Overflow.
npx -y skills add redis/agent-skills --skill redis-clustering --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
prisma/skills
firebase/agent-skills
Dexploarer/hyper-forge
itsmostafa/aws-agent-skills