Workshop Facilitation
Plugin Verified ActiveFacilitate workshop sessions with consistent pacing, options, and progress tracking.
To standardize and enhance the facilitation of interactive product management workshops, ensuring consistent pacing, clear decision-making, and predictable progress for users and AI agents.
Features
- One-step-at-a-time interaction
- Session entry mode selection (Guided, Context dump, Best guess)
- Clear progress visibility (e.g., Context Qx/8)
- Adaptive recommendations at decision points
- Flexible response parsing for multi-select options
- Interruption-safe flow with meta-question handling
Use Cases
- Running structured product strategy sessions with clear facilitation
- Guiding users through discovery interview preparation with adaptive questions
- Facilitating prioritization exercises with consistent options and progress tracking
- Ensuring AI agents follow a standardized interactive protocol for complex tasks
Non-Goals
- Providing specific PM frameworks or content; it only provides the facilitation structure.
- Replacing the need for well-defined interactive skills; it enhances them.
- Handling complex state management beyond the current session flow.
Installation
First, add the marketplace
/plugin marketplace add deanpeters/Product-Manager-Skills/plugin install workshop-facilitation@pm-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Product Sense Interview Answer
100Structure a spoken product-sense interview answer with segmentation and MVP tradeoffs.
Problem Framing Canvas
100Guide teams through MITRE's Problem Framing Canvas for clearer problem statements.
Discovery Interview Prep
100Plan customer discovery interviews with the right goal, segment, constraints, and method.
User Story Mapping Workshop
95Run a user story mapping workshop with adaptive questions and structured output.
Customer Journey Map
95Create a customer journey map across stages, touchpoints, actions, emotions, and metrics.
Learning Output Style
78Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)