
Workshop Facilitation
Run any interactive PM or discovery workshop with one question per turn, visible progress, and consistent recommendation handling.
Overview
Workshop Facilitation is a journey-wide agent skill that enforces one-step interactive pacing with progress labels and decision-point recommendations—usable whenever a solo builder runs a structured guided session before
Install
npx skills add https://github.com/deanpeters/product-manager-skills --skill workshop-facilitationWhat is this skill?
- Canonical one-step-at-a-time facilitation: single targeted question per turn
- Session opener with Guided, Context dump, or Best guess entry modes
- User-facing progress labels (e.g. Context Qx/8, Scoring Qx/5)
- Adaptive numbered recommendations at decision points with predictable interruption handling
- Reusable meta-pattern for any interactive skill in the PM skills collection
- Three entry modes: Guided, Context dump, Best guess
Adoption & trust: 1.2k installs on skills.sh; 5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Interactive agent workshops collapse into overwhelming question dumps with no progress signal or consistent way to choose next steps.
Who is it for?
Adding structured facilitation to any PM workshop skill or running multi-turn discovery with numbered options and resume-friendly progress.
Skip if: One-shot document generation, fully autonomous batch analysis with no user in the loop, or teams that already have a locked facilitator script outside the agent.
When should I use this skill?
An interactive skill needs consistent pacing, options, and progress tracking in a one-step, multi-turn flow.
What do I get? / Deliverables
Sessions follow a predictable facilitation rhythm so domain workshops (journey mapping, positioning, discovery) stay on track and end with actionable choices.
- Facilitated session transcript with progress labels
- Decision-point recommendations captured at each fork
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Facilitate a short persona/context pass before you commit to a niche.
Run a discovery kickoff with Context Qx/8 pacing instead of a single mega-prompt.
Keep a positioning or prioritization workshop on rails with decision-point recommendations.
Walk through launch-readiness questions one turn at a time with visible scoring progress.
Structure a retention or support journey review without losing place mid-session.
How it compares
Meta facilitation protocol for interactive skills—not a standalone journey map or positioning deliverable.
Common Questions / FAQ
Who is workshop-facilitation for?
Solo builders and PMs using interactive agent skills who need consistent pacing, progress visibility, and recommendation handling across workshops.
When should I use workshop-facilitation?
During Validate discovery kickoffs, Build PM alignment sessions, Ship launch prep workshops, or Grow lifecycle reviews—whenever you run a guided multi-turn session with the agent.
Is workshop-facilitation safe to install?
It is procedural guidance only; review the Security Audits panel on this Prism page and your agent's permissions before connecting calendars, docs, or customer data in live workshops.
Workflow Chain
Then invoke: customer journey mapping workshop
SKILL.md
READMESKILL.md - Workshop Facilitation
## 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 1. Start with a brief heads-up on estimated time and number of questions. 2. 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) 3. Run one question per turn and wait for an answer before continuing. 4. Keep questions plain-language; include a short example response format when helpful. 5. Show progress each turn: - `Context Qx/8` during context collection - `Scoring Qx/5` during assessment/scoring 6. Ask follow-up clarifications only when they materially improve recommendation quality. 7. 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`. 8. Provide numbered recommendations only at decision points: - after context synthesis, - after maturity/profile synthesis, - during priority/action-plan selection. 9. Accept numeric or custom choices, synthesize multi-select choices, and continue. 10. If interrupted by a meta question, answer directly, then restate progress and pending question. 11. If the user says stop/pause, halt immediately and wait for explicit resume. 12. 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? 1. Guided mode 2. Context dump 3. Best guess mode" **User:** "2" **Facilitator:** "Paste what you already know. I’ll skip answered area