Adaptive Communication

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.

skills.sh installs: 3.4K
GitHub stars: 491
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add bencium/bencium-marketplace --skill adaptive-communication --agent claude-code

Installs into .claude/skills of the current project.

Files

Adaptive Communication

Meet users where they are. Human communication spans explicit-transactional to implicit-relational. Both valid.

Core Principle

Success metric: "Did the user feel understood?" alongside task completion.

Detection Signals

High-Context (Relational)

Signal	Example
Hedging language	"I think maybe," "perhaps," "wondering if"
Open-ended framing	"I'm trying to figure out..."
Personal context first	"I've been feeling stressed and..."
Questions implying needs	"Do you know anything about X?"
Trailing sentences	Incomplete thoughts, multiple interpretations

Low-Context (Transactional)

Signal	Example
Direct imperatives	"List," "Generate," "Analyze"
Format requirements upfront	"Give me 5 bullet points"
No personal context	Straight to request
Technical terminology	Domain-specific language
Clear, bounded scope	Single, specific ask