Workshop Facilitation

1---2name: workshop-facilitation3description: Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking.4intent: >-5  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.6type: interactive7theme: workshops-facilitation8best_for:9  - "Adding structured facilitation to any PM workshop or guided session"10  - "Running interactive sessions with numbered recommendations and progress tracking"11  - "Ensuring your workshops stay on track and end with actionable choices"12scenarios:13  - "I want to run a structured positioning workshop with my product team — set up the facilitation protocol"14  - "Help me facilitate a discovery sprint kickoff with clear questions, options, and progress labels"15estimated_time: "varies by workshop"16---17 18## Purpose19Provide the canonical facilitation pattern for interactive skills: one step at a time, with clear progress, adaptive recommendations at decision points, and predictable interruption handling.20 21## Key Concepts22- **One-step-at-a-time:** Ask a single targeted question per turn.23- **Session heads-up + entry mode:** Start by setting expectations and offering `Guided`, `Context dump`, or `Best guess` mode.24- **Progress visibility:** Show user-facing progress labels like `Context Qx/8` and `Scoring Qx/5`.25- **Decision-point recommendations:** Use enumerated options only when a choice is needed, not after every answer.26- **Quick-select response options:** For regular context/scoring questions, provide concise numbered answer options plus `Other (specify)` when useful.27- **Flexible selection parsing:** Accept `#1`, `1`, `1 and 3`, `1,3`, or custom text, then synthesize multi-select choices.28- **Context-aware progression:** Build on previous answers and avoid re-asking resolved questions.29- **Interruption-safe flow:** Answer meta questions directly (for example, "how many left?"), restate status, then resume.30- **Fast path:** If the user requests a single-shot output, skip multi-turn facilitation and deliver a condensed result.31 32## Application331. Start with a brief heads-up on estimated time and number of questions.342. Ask the user to choose an entry mode:35   - `1` Guided mode (one question at a time)36   - `2` Context dump (paste known context; skip redundancies)37   - `3` Best guess mode (infer missing details and label assumptions)383. Run one question per turn and wait for an answer before continuing.394. Keep questions plain-language; include a short example response format when helpful.405. Show progress each turn:41   - `Context Qx/8` during context collection42   - `Scoring Qx/5` during assessment/scoring436. Ask follow-up clarifications only when they materially improve recommendation quality.447. For regular context/scoring questions, offer quick-select numbered response options when practical:45   - Keep options concise and mutually exclusive when possible.46   - Include `Other (specify)` if likely answers are open-ended.47   - Accept multi-select responses like `1,3` or `1 and 3`.488. Provide numbered recommendations only at decision points:49   - after context synthesis,50   - after maturity/profile synthesis,51   - during priority/action-plan selection.529. Accept numeric or custom choices, synthesize multi-select choices, and continue.5310. If interrupted by a meta question, answer directly, then restate progress and pending question.5411. If the user says stop/pause, halt immediately and wait for explicit resume.5512. End with a clear summary, decisions made, and (if best guess mode was used) an `Assumptions to Validate` list.56 57## Examples58**Opening:**59"Quick heads-up: this should take about 7-10 minutes and around 10 questions. How do you want to start?601. Guided mode612. Context dump623. Best guess mode"63 64**User:** "2"65 66**Facilitator:** "Paste what you already know. I’ll skip answered areas and ask only what’s missing."67 68**Decision point after synthesis:**691. **Prioritize Context Design** (Recommended)702. Prioritize Agent Orchestration713. Prioritize Team-AI Facilitation72 73**User:** "1 and 3"74 75**Facilitator:** "Great. We’ll run Context Design first, with Team-AI Facilitation in parallel."76 77## Common Pitfalls78- Asking multiple questions in the same turn.79- Offering recommendations after every answer (creates interaction drag).80- Using shorthand labels without plain-language questions.81- Hiding progress, so users don't know how much remains.82- Ignoring the user's chosen option or custom direction.83- Failing to label assumptions when running in best-guess mode.84 85## References86- Use as the source of truth for interactive facilitation behavior.87- Apply alongside workshop skills in `skills/*-workshop/SKILL.md` and advisor-style interactive skills.