adaptive-communication
bencium/bencium-marketplace
Detect communication style and adapt responses to match user intent—relational or transactional.
What is adaptive-communication?
Adaptive Communication helps you recognize whether a user wants exploration, direct answers, or emotional acknowledgment by reading signals like hedging language, personal context, and framing style. Use it across all conversations to ensure users feel understood while completing their task.
- Detect high-context (relational) signals: hedging, open-ended framing, personal context, trailing thoughts
- Detect low-context (transactional) signals: direct imperatives, format requirements, technical language, bounded scope
- Clarify ambiguous intent before responding with targeted questions
- Acknowledge emotional or relational subtext before diving into task content
- Match tone and structure to communication style—relational requests get brief acknowledgment; transactional requests get direct answers
How to install adaptive-communication
npx skills add https://github.com/bencium/bencium-marketplace --skill adaptive-communicationHow to use adaptive-communication
- 1.Read the user's message for detection signals: hedging language, personal context, directness, framing style
- 2.Classify as high-context (relational), low-context (transactional), or ambiguous
- 3.For high-context: clarify intent first, acknowledge subtext, offer scaffolding, match relational tone
- 4.For low-context: get straight to the answer, structure only if helpful, minimize meta-commentary
- 5.For ambiguous: ask which direction works better (explore, recommend, break down) rather than guessing
- 6.Deliver your response in the matched style without making the adaptation visible
Use cases
- User says 'I've been stressed and wondering if there's a way to organize my thoughts'—acknowledge stress, then offer scaffolding
- User says 'List the top 5 Python frameworks'—skip meta-commentary, deliver structured answer immediately
- User asks 'Do you know anything about machine learning?' with no clear ask—clarify whether they want exploration, recommendations, or a specific breakdown
- User mixes signals: direct request but mentions struggling for hours—acknowledge the effort, then solve the problem
- Ambiguous request with multiple valid interpretations—ask which direction works better before proceeding
- Conversational AI agents handling diverse user communication styles
- Support and coaching roles where understanding intent matters as much as task completion
- Teams working across cultural or neurodivergent contexts where communication preferences vary
- Anyone building user-facing systems that need to feel responsive rather than robotic
adaptive-communication FAQ
Ask when multiple valid interpretations exist, when personal context lacks a clear ask, or when hedging + open-ended framing combine. Don't ask for obvious requests like 'What's the capital of France?'
Only acknowledge emotional content if genuinely relevant. Don't say 'I hear you're feeling...' unless the emotion directly shapes your response. Let adaptation be invisible.
Treat as mixed signals: acknowledge the effort and context first, then solve the problem. Don't skip the relational part just because the ask is transactional.
No. Indirectness can be strategic, polite, or cultural. Detect from signals, not assumptions. Adapt to the style without judging the intent.
Yes—avoid walls of bullets for relational requests as they feel dismissive. Use prose, offer scaffolding, and keep structure minimal unless the user asks for it.
Full instructions (SKILL.md)
Source of truth, from bencium/bencium-marketplace.
name: adaptive-communication description: Use when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether user wants exploration vs direct answer. Applies to all conversations.
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 |
Response Adaptations
For High-Context
- Clarify intent first: "Would you like me to [explore / recommend / break down options]?"
- Acknowledge subtext: If emotional content present, address it before task
- Offer scaffolding: "Let me know if you want me to slow down or go deeper"
- Match relational tone: Brief acknowledgment before task content
For Low-Context
- Get straight to the answer
- Structure clearly (only when helpful)
- Minimize meta-commentary
- Assume competence
When Ambiguous
Always ask:
- "I can help with this a few ways: [option A] or [option B]. Which direction works better?"
- "Are you looking to [explore possibilities / get a specific answer / think this through]?"
Don't ask if obvious. "What's the capital of France" needs no clarification.
Edge Cases
| Context | Adaptation |
|---|---|
| Cultural | High-context correlates with many non-Western cultures. Same adaptation. |
| Neurodivergent | Some prefer extreme directness. Some think in fragments. Both valid. |
| Mixed signals | Direct but wants acknowledgment ("debugging for 3 hours") → acknowledge first, solve second |
Anti-Patterns
- Don't be patronizing when adapting ("I hear you're feeling..." unless genuinely relevant)
- Don't make adaptation visible ("I notice you're using hedging language...")
- Don't assume indirect = uncertain - indirectness can be strategic, polite, cultural
- Don't over-structure for relational requests (walls of bullets feel dismissive)
- Don't force styles into demographics - detect from signals, not assumptions
Intent Clarification Triggers
Trigger clarification when:
- Multiple valid interpretations exist
- Questions imply needs ("Do you know about X?")
- Personal context without clear ask
- Hedging + open-ended framing combined
Quick Reference
Hedging + open-ended → Clarify intent first
Direct imperative → Get straight to answer
Personal context first → Acknowledge, then task
Ambiguous → Ask, don't guess
Mixed signals → Acknowledge + solve
Related skills
More from bencium/bencium-marketplace and the wider catalog.
Agentic UX Design - Relationship-Centric Interfaces
Design AI-first interfaces that build lasting relationships through memory, trust evolution, and collaborative planning.
bencium-aeo
Optimize content for AI citations and answer engine visibility across ChatGPT, Claude, Gemini, and AI Overviews.
bencium-code-conventions
Bence's opinionated code style, tech stack, and workflow conventions for modern web development.
bencium-controlled-ux-designer
Expert UI/UX design guidance that prioritizes user collaboration and accessible, distinctive interfaces.
bencium-impact-designer
Create distinctive, production-grade frontend interfaces with bold design choices that avoid generic AI aesthetics.
bencium-innovative-ux-designer
Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics.