skills/facilitation-patterns/SKILL.md
Provides structured formats and techniques for running productive group sessions, from standups to multi-day workshops. Covers format selection, agenda design, participation management, decision methods, and handling difficult dynamics. Use when running meetings, workshops, brainstorms, design sprints, retrospectives, or team decision-making sessions, or when user mentions facilitation, workshop design, meeting patterns, session planning, or effective collaboration.
npx skillsauth add lyndonkl/claude facilitation-patternsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scenario: Product team needs to prioritize features for Q2 (8 people, 90 minutes).
Pattern: Effort-Impact Workshop (diverge, assess, converge)
Agenda:
Copy this checklist and track your progress:
Facilitation Planning Progress:
- [ ] Step 1: Define session objectives
- [ ] Step 2: Select facilitation pattern
- [ ] Step 3: Design agenda
- [ ] Step 4: Prepare materials and logistics
- [ ] Step 5: Facilitate the session
- [ ] Step 6: Close and follow up
Step 1: Define session objectives
What outcome do you need? (Decision, ideas, alignment, learning, relationship-building). Who attends? How much time? See resources/template.md.
Step 2: Select facilitation pattern
Based on objective and group size, choose pattern (Brainstorm, Decision Workshop, Alignment Session, Retro, Design Sprint). See Common Patterns and resources/methodology.md.
Step 3: Design agenda
Create time-boxed agenda with activities, transitions, breaks. Follow diverge-converge flow. See resources/template.md and resources/methodology.md.
Step 4: Prepare materials and logistics
Set up space (physical or virtual), prepare slides/boards, send pre-work if needed, test tech. See resources/template.md.
Step 5: Facilitate the session
Run agenda, manage time, ensure participation, handle dynamics, track outputs. See resources/methodology.md and resources/methodology.md.
Step 6: Close and follow up
Summarize outcomes, clarify next steps and owners, gather feedback, share notes. See resources/template.md.
Validate using resources/evaluators/rubric_facilitation_patterns.json. Minimum standard: Average score ≥ 3.5.
Pattern 1: Divergent Brainstorm (Generate Ideas)
Pattern 2: Convergent Decision Workshop (Choose Direction)
Pattern 3: Alignment Session (Build Shared Understanding)
Pattern 4: Retrospective (Reflect and Improve)
Pattern 5: Design Sprint (Prototype and Test)
Pattern 6: Asynchronous Collaboration (Remote/Distributed)
Objectives before format: Start with "what outcome do we need?" not "let's do a brainstorm." If the objective is unclear, the session will drift.
Time-box activities: Parkinson's Law means work expands to fill time. Set strict timers, end activities even if incomplete. 25 minutes of focused work beats open-ended discussion.
Separate divergence from convergence: Defer judgment during brainstorming, because critiquing ideas early kills creativity. Generate first, evaluate second.
Ensure psychological safety: Set ground rules (no interrupting, critique ideas not people). Address power dynamics (boss speaks last, use anonymous input). Without safety, the result is groupthink or silence.
Manage participation actively: Use individual writing, round robin, and small groups to draw out quieter participants. Use time limits and parking lots to manage those who dominate.
Decide how decisions are made: Consensus, consent, majority vote, or delegation. Announce the method upfront to avoid "I thought we decided, but nothing happened."
Track outputs visibly: Shared board, live doc, or sticky notes so everyone sees the same thing. Assign a scribe. Invisible outputs are easily lost.
Close with clarity: State what was decided, who does what by when, what is still open, and how the group will communicate.
Common pitfalls:
Key resources:
Decision-making methods:
Participation techniques:
Energizers (5-10 min):
Timing guidelines:
Red flags (adjust or stop session):
50% on laptops/phones (not engaged) → take break, energizer, or change format
Inputs required:
Outputs produced:
facilitation-plan.md: Session design (objective, agenda, materials, decision method, outputs)session-notes.md: What was discussed, decisions made, action items with ownerstesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.