settled-reach/whatsinagame/templates/.claude/skills/workshop-start/SKILL.md

name, description

name	description
workshop-start	Start a multi-agent design workshop from a workshop brief. Use when the user says "start workshop", "run workshop", or invokes /workshop-start. Parses the brief, creates a team, and spawns agents as teammates.

Start Workshop

Prerequisites

A workshop brief must exist at docs/workshops/{name}/{name}-workshop-brief.md containing:

• Participants line (comma-separated agent names)
• Questions for participants sections with numbered questions tagged by agent name
• Workshop Format section defining number of rounds and their purpose

Workflow

1. Parse the Brief

Read the workshop brief. Extract:

• Workshop name (from directory name)
• Participant list (from **Participants:** line)
• Per-participant questions (scan for **{AgentName}**: patterns in questions sections)
• Round count and round descriptions (from **Workshop Format** section)

2. Create Team

TeamCreate: team_name = "{workshop-name}", description from brief title

3. Always-Present Agents

Two agents join every workshop regardless of the participant list:

Agent	Role	Task	Participates in discussion?
Documenter	Librarian	Captures all decisions, questions, dissent, consensus. Writes workshop-notes.md per round, produces final workshop-outcomes.md.	No — observes and records only
Project Manager	Sprint prep	Suggest adding when outputs include tickets. Creates tickets from decisions, links to sprint backlog.	No — execution prep only

The documenter and PM are never dismissed early. If the user reduces the team mid-workshop, keep them present. Documenting everything prevents loss of valuable information.

4. Create Tasks (Round 1)

One task per participant containing:

• Instruction to read the full brief at its path
• The specific questions assigned to that participant (extracted from all layers)
• The output format from the brief's round description
• IMPORTANT — file output requirement: Instruct each agent to write their full output to docs/workshops/{name}/{agent}-round{N}.md (e.g., docs/workshops/architecture/designer-round1.md). Agents must write to disk, not just send messages. This ensures the documenter and other agents can read all outputs directly without relying on message forwarding.

One task for the documenter: "Document Round N — read all agent output files at docs/workshops/{name}/*-round{N}.md and capture decisions, questions, and dissent."

Assign all tasks using TaskUpdate with owner = agent name.

5. Spawn Agents

Use the Task tool to spawn each agent as a teammate. Each call should:

• Set team_name to the workshop team name
• Set name to the agent name (e.g., "designer")
• Set subagent_type to the matching agent type (check .claude/agents/ for available types)
• Provide a prompt telling the agent to check TaskList for their assigned task

Spawn all agents in parallel (one Task call per agent in a single message). Agents will appear as teammates in the Claude Code UI and pick up their tasks from the shared task list.

For large workshops (>6 agents), spawn participants in batches to avoid overwhelming the system. Always-present agents (documenter, PM) can run in background via run_in_background: true.

6. Monitor

• TaskList to check progress
• SendMessage to nudge idle agents or provide clarification
• Agents work autonomously — claim tasks, read the brief, produce responses

7. Between Rounds

When all Round N tasks are complete:

1. Verify all agents wrote output files to docs/workshops/{name}/. If any are missing, nudge the agent or extract from their message and write the file yourself.
2. Documenter reads all *-round{N}.md files and produces round summary in round-{N}-notes.md
3. Create Round N+1 tasks (integration pass, synthesis, etc.) — include the same file output requirement
4. Assign to agents with TaskUpdate
5. Agents continue working

8. Wrap Up

Always ask the user before wrapping up. There may be more to discuss or additional rounds needed. Only proceed to wrap-up when the user confirms.

Wrap-up sequence:

1. Documenter produces final workshop-outcomes.md from accumulated notes
2. If PM is present, PM creates tickets from decided items
3. Send shutdown_request to all agents (documenter and PM last, after they finish their output tasks)
4. TeamDelete to clean up

Agent Type Reference

Map agent names to their subagent_type by checking .claude/agents/. Common workshop roles:

Role	Typical workshop contribution
Systems Designer	Mechanics, interactions, system balance
Player Experience	Feel, emotional response, wow moments
Architect	Feasibility, performance, architecture
UI Developer	Interface patterns, layout, interaction flows
Backend Developer	Server-side systems, data flow
Narrative Designer	Story, dialogue, character depth
Visual Designer	Art direction, visual treatment, aesthetics
Content Author	In-game text, voice, tone
Worldbuilder	Setting, factions, lore, consistency
Audio Designer	Soundscape, spatial audio
QA Engineer	Test plans, verification, quality