Adaptive Communication
Tune how your agent responds when user intent is ambiguous—relational vs transactional—so exploration feels understood without over-delivering specs.
Overview
adaptive-communication is a journey-wide agent skill that matches replies to high-context or low-context user signals so solo builders feel understood before the agent commits to a deliverable.
Install
npx skills add https://github.com/bencium/bencium-marketplace --skill adaptive-communicationWhat is this skill?
- Dual-mode detection: high-context (hedging, open-ended, personal context) vs low-context (imperatives, format specs, bou
- Success metric pairs task completion with "Did the user feel understood?"
- High-context playbook: clarify intent, acknowledge subtext, offer scaffolding before diving into implementation
- Low-context playbook: execute directly with specified format and scope
- Explicit invoke triggers: ambiguous intent, hedging, open-ended framing, personal context before requests
- Two signal tables: high-context (relational) and low-context (transactional)
- Documented response adaptations for each mode
Adoption & trust: 1.1k installs on skills.sh; 273 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You hedge or share context and the agent jumps straight to code or a wall of assumptions instead of clarifying what you actually want.
Who is it for?
Any solo builder using agents for open-ended product work where tone and ambiguity change what "done" looks like.
Skip if: Fully automated pipelines with fixed JSON inputs and no natural-language chat, or when the user already gave explicit format and scope.
When should I use this skill?
Detect ambiguous user intent, hedging language, open-ended framing, personal context before requests, or uncertainty between exploration vs direct answer.
What do I get? / Deliverables
The agent first classifies relational vs transactional intent, then either scaffolds exploration or executes a bounded task—improving understood-ness alongside completion.
- Intent-aligned replies (clarifications, scaffolding, or direct execution)
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
User says "maybe there's a market for…"—agent offers exploration paths instead of a fake PRD.
Open-ended "trying to figure out MVP" triggers scaffolding and option tradeoffs before coding.
Direct "list API endpoints as a table" gets immediate structured output without therapeutic preamble.
Stressed preamble about downtime gets acknowledgment, then a bounded incident checklist.
Hedged ask about "getting the word out" clarifies whether user wants channels, calendar, or draft posts.
How it compares
Conversational meta-skill—not a brainstorming template pack or a technical linter.
Common Questions / FAQ
Who is adaptive-communication for?
Indie developers and solo founders who rely on Claude Code, Cursor, or similar agents for mixed exploratory and direct requests.
When should I use adaptive-communication?
During Idea research chats, Validate scoping, Build implementation, Ship reviews, Launch copy drafts, Grow analytics questions, or Operate incident threads whenever intent, hedging, or personal context makes the right response unclear.
Is adaptive-communication safe to install?
It only shapes response style—review the Security Audits panel on this Prism page for the marketplace skill package itself.
SKILL.md
READMESKILL.md - Adaptive Communication
# 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 1. **Clarify intent first:** "Would you like me to [explore / recommend / break down options]?" 2. **Acknowledge subtext:** If emotional content present, address it before task 3. **Offer scaffolding:** "Let me know if you want me to slow down or go deeper" 4. **Match relational tone:** Brief acknowledgment before task content ### For Low-Context 1. Get straight to the answer 2. Structure clearly (only when helpful) 3. Minimize meta-commentary 4. 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 ```