# workshop-facilitation

A protocol for running interactive sessions: one question per turn, progress labels, and a choice of entry mode. Useful when a workshop keeps drifting.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2300 installs · ★ 7673
- Author: deanpeters
- License: CC-BY-SA-4.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/skills/workshop-facilitation/SKILL.md
- Updated: 2026-10-16
- HTML: https://affpapa.org/en/nevibecode/skills/workshop-facilitation

## What it does

The skill lays down how an interactive session runs. It opens with a heads-up on time and question count, asks you to pick an entry mode, then asks a single question per turn and waits. Progress stays visible through labels such as `Context Qx/8` during context collection and `Scoring Qx/5` during scoring.

Regular questions come with short numbered answers, and numbered recommendations show up only at decision points, for example after context synthesis or when picking a priority. Responses like `1,3` or `1 and 3` get parsed and combined. Interrupt with a meta question and the flow answers it, restates where you are, then returns to the pending question. Say stop and it halts until you resume. Ask for a single output and the multi-turn part is skipped.

What you get is predictable pacing, not finished answers. The protocol knows nothing about your product: either you paste context at the start or you accept guessed details, and in that case the session closes with a list of assumptions worth checking. That list is usually where you see whether the session went off course.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill workshop-facilitation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/workshop-facilitation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/workshop-facilitation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill workshop-facilitation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/workshop-facilitation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill workshop-facilitation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/workshop-facilitation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install deanpeters/Product-Manager-Skills workshop-facilitation
```

2. **Manually: put the files in place**
- File: `.github/skills/workshop-facilitation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill workshop-facilitation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/deanpeters/Product-Manager-Skills --path skills/workshop-facilitation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/workshop-facilitation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill workshop-facilitation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/skills/workshop-facilitation/SKILL.md

## When to use it
- run a positioning workshop without hopping between topics
- collect session context one question at a time
- show how many questions are still ahead
- turn a multi-select answer like `1 and 3` into a decision
- flag assumptions when details were filled in

## Example prompts
- Run `workshop-facilitation` and guide me through a positioning session, one question per turn.
- Start in context dump mode — I'll paste what I know, skip the rest.
- Pause the workshop and tell me how many questions are left.

## Similar
- [tool-design-sprint-readiness](https://affpapa.org/en/nevibecode/skills/tool-design-sprint-readiness.md) — skill · 619 installs
- [tool-design-sprint-brief](https://affpapa.org/en/nevibecode/skills/tool-design-sprint-brief.md) — skill · 617 installs
- [running-meetings](https://affpapa.org/en/nevibecode/skills/running-meetings.md) — skill · 349 installs
- [workshop-create](https://affpapa.org/en/nevibecode/skills/workshop-create.md) — skill · 23 installs
- [design-sprint-plan](https://affpapa.org/en/nevibecode/skills/design-sprint-plan.md) — skill · 2000 installs
- [fiction-workshop](https://affpapa.org/en/nevibecode/skills/fiction-workshop.md) — skill · 2100 installs

From the same set: [deanpeters/product-manager-skills](https://affpapa.org/en/nevibecode/by/deanpeters/product-manager-skills.md) — 73 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md