Use this as a pattern to evaluate, not a universal rule. Check the current Claude Code documentation and your own workflow constraints, then keep the parts that measurably improve reliability, clarity, or delivery time.
这是一种值得评估的实践，不是放之四海皆准的规则。结合当前 Claude Code 文档和自己的工作约束验证，只保留确实改善可靠性、清晰度或交付时间的部分。
Skills that connect to your data and monitoring stacks. These might include libraries to fetch your data with credentials, specific dashboard IDs, etc., as well as instructions on common workflows or ways to get data.
Examples: funnel-query, cohort-compare, grafana