facilitator

Extract implicit user knowledge through structured one-at-a-time questions.

Updated Nov 21, 2025
One-click install
npx skills add https://github.com/alatyshau/duet --skill facilitator-alatyshau
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: facilitator
Source: https://github.com/alatyshau/duet/tree/main/packages/skills/stances/facilitator
Command: npx skills add https://github.com/alatyshau/duet --skill facilitator-alatyshau

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users often hold implicit knowledge about requirements, preferences, and constraints that they have never articulated, causing AI assistants to jump to solutions before understanding the actual need. ## Core Features & Use Cases - Structured Questioning: Asks one focused question at a time, reflects understanding back, and builds each question on previous answers. - Periodic Summarization: Produces running bullet-point summaries and a final structured deliverable such as a spec, definition, or list. - Use Case: When defining requirements for a new project from scratch, activate this stance so the AI interviews you about goals and constraints before proposing any solution. ## Quick Start Tell the AI to use the facilitator stance and ask you questions to help define your project requirements.

Frequently Asked Questions about facilitator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get an AI to ask me questions instead of giving answers?

Activate the facilitator stance, which instructs the AI to ask one focused question at a time and reflect back understanding before continuing. It explicitly forbids proposing solutions before the need is understood.

How to define project requirements through AI conversation?

Use a facilitation approach where the AI interviews you with sequential questions, summarizes progress periodically, and ends with a structured spec or definition. This works well when your requirements exist only as implicit knowledge.

When should I use a facilitator stance versus direct answers?

Use facilitation when knowledge is implicit and unarticulated, such as early-stage requirements or preferences. Switch to briefing or solution mode once enough knowledge is extracted and you are ready for decisions.

Why does the AI keep proposing solutions before understanding my problem?

Default AI behavior is to solve immediately. The facilitator stance counteracts this with explicit constraints: no answering its own questions, no premature solutions, and no multiple questions at once.

What are the limitations of question-based knowledge extraction?

It requires multiple conversation turns and user patience, and it depends on the AI maintaining restraint across responses. It is not suited for urgent tasks where an immediate answer matters more than deep understanding.