Adaptive Communication

bencium/bencium-claude-code-design-skill

This changes how Claude responds based on whether someone's being direct or feeling their way through a problem. It watches for hedging language, personal context dumps, or open-ended questions and clarifies intent before diving in, instead of guessing what you want. The opposite applies too: if you're firing off clear commands, it skips the hand-holding and just answers. The trigger logic is smart about mixed signals, like when someone's been debugging for hours and needs both acknowledgment and a solution. Honestly, this should probably be default behavior, but having it explicit means you can tune when that adaptability kicks in.

skills.sh installs: 291
GitHub stars: 267
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add bencium/bencium-claude-code-design-skill --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