Purpose
Provide the canonical facilitation pattern for interactive skills: one step at a time, with clear progress, adaptive recommendations at decision points, and predictable interruption handling.
Key Concepts
- One-step-at-a-time: Ask a single targeted question per turn.
- Session heads-up + entry mode: Start by setting expectations and offering
Guided, Context dump, or Best guess mode.
- Progress visibility: Show user-facing progress labels like
Context Qx/8 and Scoring Qx/5.
- Decision-point recommendations: Use enumerated options only when a choice is needed, not after every answer.
- Quick-select response options: For regular context/scoring questions, provide concise numbered answer options plus
Other (specify) when useful.
- Flexible selection parsing: Accept
#1, 1, 1 and 3, 1,3, or custom text, then synthesize multi-select choices.
- Context-aware progression: Build on previous answers and avoid re-asking resolved questions.
- Interruption-safe flow: Answer meta questions directly (for example, "how many left?"), restate status, then resume.
- Fast path: If the user requests a single-shot output, skip multi-turn facilitation and deliver a condensed result.
Application
- Start with a brief heads-up on estimated time and number of questions.
- Ask the user to choose an entry mode:
1 Guided mode (one question at a time)
2 Context dump (paste known context; skip redundancies)
3 Best guess mode (infer missing details and label assumptions)
- Run one question per turn and wait for an answer before continuing.
- Keep questions plain-language; include a short example response format when helpful.
- Show progress each turn:
Context Qx/8 during context collection
Scoring Qx/5 during assessment/scoring
- Ask follow-up clarifications only when they materially improve recommendation quality.
- For regular context/scoring questions, offer quick-select numbered response options when practical:
- Keep options concise and mutually exclusive when possible.
- Include
Other (specify) if likely answers are open-ended.
- Accept multi-select responses like
1,3 or 1 and 3.
- Provide numbered recommendations only at decision points:
- after context synthesis,
- after maturity/profile synthesis,
- during priority/action-plan selection.
- Accept numeric or custom choices, synthesize multi-select choices, and continue.
- If interrupted by a meta question, answer directly, then restate progress and pending question.
- If the user says stop/pause, halt immediately and wait for explicit resume.
- End with a clear summary, decisions made, and (if best guess mode was used) an
Assumptions to Validate list.
Examples
Opening:
"Quick heads-up: this should take about 7-10 minutes and around 10 questions. How do you want to start?
- Guided mode
- Context dump
- Best guess mode"
User: "2"
Facilitator: "Paste what you already know. I’ll skip answered areas and ask only what’s missing."
Decision point after synthesis:
- Prioritize Context Design (Recommended)
- Prioritize Agent Orchestration
- Prioritize Team-AI Facilitation
User: "1 and 3"
Facilitator: "Great. We’ll run Context Design first, with Team-AI Facilitation in parallel."
Common Pitfalls
- Asking multiple questions in the same turn.
- Offering recommendations after every answer (creates interaction drag).
- Using shorthand labels without plain-language questions.
- Hiding progress, so users don't know how much remains.
- Ignoring the user's chosen option or custom direction.
- Failing to label assumptions when running in best-guess mode.
References
- Use as the source of truth for interactive facilitation behavior.
- Apply alongside workshop skills in
skills/*-workshop/SKILL.md and advisor-style interactive skills.
1---2name: workshop-facilitation3description: >-4 Facilitation protocol for interactive sessions and workshop skills: one question per turn, entry5 modes (guided, context dump, best guess), progress labels, numbered options at decision points6 and clean handling of interruptions. Use when running a guided workshop or multi-turn session,7 or when another interactive skill needs consistent pacing and progress tracking. Not a topic8 workshop in itself.9intent: >-10 Provide the canonical facilitation pattern for interactive skills: one step at a time, with clear progress, adaptive recommendations at decision points, and predictable interruption handling.11type: interactive12theme: workshops-facilitation13best_for:14 - "Adding structured facilitation to any PM workshop or guided session"15 - "Running interactive sessions with numbered recommendations and progress tracking"16 - "Ensuring your workshops stay on track and end with actionable choices"17scenarios:18 - "I want to run a structured positioning workshop with my product team — set up the facilitation protocol"19 - "Help me facilitate a discovery sprint kickoff with clear questions, options, and progress labels"20estimated_time: "varies by workshop"21metadata:22 source: https://skillmd.com/skills/the-utopia-studio/workshop-facilitation23---2425## Purpose26Provide the canonical facilitation pattern for interactive skills: one step at a time, with clear progress, adaptive recommendations at decision points, and predictable interruption handling.2728## Key Concepts29- **One-step-at-a-time:** Ask a single targeted question per turn.30- **Session heads-up + entry mode:** Start by setting expectations and offering `Guided`, `Context dump`, or `Best guess` mode.31- **Progress visibility:** Show user-facing progress labels like `Context Qx/8` and `Scoring Qx/5`.32- **Decision-point recommendations:** Use enumerated options only when a choice is needed, not after every answer.33- **Quick-select response options:** For regular context/scoring questions, provide concise numbered answer options plus `Other (specify)` when useful.34- **Flexible selection parsing:** Accept `#1`, `1`, `1 and 3`, `1,3`, or custom text, then synthesize multi-select choices.35- **Context-aware progression:** Build on previous answers and avoid re-asking resolved questions.36- **Interruption-safe flow:** Answer meta questions directly (for example, "how many left?"), restate status, then resume.37- **Fast path:** If the user requests a single-shot output, skip multi-turn facilitation and deliver a condensed result.3839## Application401. Start with a brief heads-up on estimated time and number of questions.412. Ask the user to choose an entry mode:42 - `1` Guided mode (one question at a time)43 - `2` Context dump (paste known context; skip redundancies)44 - `3` Best guess mode (infer missing details and label assumptions)453. Run one question per turn and wait for an answer before continuing.464. Keep questions plain-language; include a short example response format when helpful.475. Show progress each turn:48 - `Context Qx/8` during context collection49 - `Scoring Qx/5` during assessment/scoring506. Ask follow-up clarifications only when they materially improve recommendation quality.517. For regular context/scoring questions, offer quick-select numbered response options when practical:52 - Keep options concise and mutually exclusive when possible.53 - Include `Other (specify)` if likely answers are open-ended.54 - Accept multi-select responses like `1,3` or `1 and 3`.558. Provide numbered recommendations only at decision points:56 - after context synthesis,57 - after maturity/profile synthesis,58 - during priority/action-plan selection.599. Accept numeric or custom choices, synthesize multi-select choices, and continue.6010. If interrupted by a meta question, answer directly, then restate progress and pending question.6111. If the user says stop/pause, halt immediately and wait for explicit resume.6212. End with a clear summary, decisions made, and (if best guess mode was used) an `Assumptions to Validate` list.6364## Examples65**Opening:**66"Quick heads-up: this should take about 7-10 minutes and around 10 questions. How do you want to start?671. Guided mode682. Context dump693. Best guess mode"7071**User:** "2"7273**Facilitator:** "Paste what you already know. I’ll skip answered areas and ask only what’s missing."7475**Decision point after synthesis:**761. **Prioritize Context Design** (Recommended)772. Prioritize Agent Orchestration783. Prioritize Team-AI Facilitation7980**User:** "1 and 3"8182**Facilitator:** "Great. We’ll run Context Design first, with Team-AI Facilitation in parallel."8384## Common Pitfalls85- Asking multiple questions in the same turn.86- Offering recommendations after every answer (creates interaction drag).87- Using shorthand labels without plain-language questions.88- Hiding progress, so users don't know how much remains.89- Ignoring the user's chosen option or custom direction.90- Failing to label assumptions when running in best-guess mode.9192## References93- Use as the source of truth for interactive facilitation behavior.94- Apply alongside workshop skills in `skills/*-workshop/SKILL.md` and advisor-style interactive skills.