This one catches when users are being indirect or tentative and adjusts how Claude responds. It looks for hedging language like "I think maybe," personal context before the actual request, or open-ended framing, then either clarifies intent first or matches the relational tone before diving into the task. When someone says "I've been debugging for 3 hours and wondering if..." it'll acknowledge that context instead of jumping straight to code. The opposite also works: direct imperatives get direct answers without the scaffolding. Honestly most useful for preventing those moments where Claude over-explains to someone who just wanted a quick answer, or steamrolls past someone who needed to think out loud first.
npx skills add https://github.com/bencium/bencium-marketplace --skill adaptive-communication