Advisory-only Kafka tuning for Confluent Cloud or Confluent Platform by priority: latency, throughput, availability, or durability. Use when asked to size a planned topic or tune an existing cluster, topic, producer, or consumer for a quantified target such as lower p99 latency or no lost acknowledged writes.
Install
npx skills add confluentinc/agent-skills --skill confluent-tuning-advisornpx skills add confluentinc/agent-skills --skill confluent-tuning-advisor -a claude-code -gnpx skills add confluentinc/agent-skills --skill confluent-tuning-advisor -a codex -ggemini skills install https://github.com/confluentinc/agent-skills.git --path skills/confluent-tuning-advisorgh skill install confluentinc/agent-skills confluent-tuning-advisorgit clone --depth 1 https://github.com/confluentinc/agent-skills /tmp/confluentinc__agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/confluentinc__agent-skills/skills/confluent-tuning-advisor ~/.claude/skills/confluent-tuning-advisor # Claude Code
cp -R /tmp/confluentinc__agent-skills/skills/confluent-tuning-advisor ~/.agents/skills/confluent-tuning-advisor # Codex, Cursor, Gemini CLI, Copilot, OpenCode