mcpField
T
team-brainstorm

team-brainstorm

github.com/catlog22Productivity2.1k65 installsUpdated 19w ago
Repository

About team-brainstorm

team-brainstorm is a skill for coordinating multi-agent ideation, intended for teams that need to generate, challenge, synthesize, and evaluate ideas. It offers Quick, Deep, and Full pipelines with a Generator-Critic loop.

Key features

  1. 01Multi-agent brainstorming coordination
  2. 02Quick, Deep, and Full pipelines
  3. 03Idea generation, challenge, and synthesis
  4. 04Generator-Critic loop
  5. 05Session status checks and resumption

Use cases

  1. 01Generate ideas from a topic in parallel
  2. 02Review assumptions behind ideas
  3. 03Synthesize and evaluate candidate approaches

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/catlog22/claude-code-workflow --skill team-brainstorm

After installing, type/team-brainstormin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

roles/challenger/
role.md
roles/coordinator/
role.md
roles/coordinator/commands/
analyze.md
dispatch.md
monitor.md
roles/evaluator/
role.md
roles/ideator/
role.md
roles/synthesizer/
role.md
specs/
pipelines.md
team-config.json

Details

From the project README

Team Brainstorm

Orchestrate multi-agent brainstorming: generate ideas → challenge assumptions → synthesize → evaluate. Supports Quick, Deep, and Full pipelines with Generator-Critic loop.

Architecture

Skill(skill="team-brainstorm", args="topic description")
                    |
         SKILL.md (this file) = Router
                    |
     +--------------+--------------+
     |                             |
  no --role flag              --role <name>
     |                             |
  Coordinator                  Worker
  roles/coordinator/role.md    roles/<name>/role.md
     |
     +-- analyze → dispatch → spawn workers → STOP
                                    |
                    +-------+-------+-------+
                    v       v       v       v
                 [ideator][challenger][synthesizer][evaluator]

Role Registry

RolePathPrefixInner Loop
coordinatorroles/coordinator/role.md——
ideatorroles/ideator/role.mdIDEA-*false
challengerroles/challenger/role.mdCHALLENGE-*false
synthesizerroles/synthesizer/role.mdSYNTH-*false
evaluatorroles/evaluator/role.mdEVAL-*false

Role Router

Parse $ARGUMENTS:

  • Has --role <name> → Read roles/<name>/role.md, execute Phase 2-4
  • No --role → @roles/coordinator/role.md, execute entry router

Shared Constants

  • Session prefix: BRS
  • Session path: .workflow/.team/BRS-<slug>-<date>/
  • CLI tools: ccw cli --mode analysis (read-only), ccw cli --mode write (modifications)
  • Message bus: mcp__ccw-tools__team_msg(session_id=<session-id>, ...)

Worker Spawn Template

Coordinator spawns workers using this template:

Agent({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: "brainstorm",
  name: "<role>",
  run_in_background: true,
  prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: brainstorm
requirement: <topic-description>
inner_loop: false

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})

Parallel ideator spawn (Full pipeline with N angles):

When Full pipeline has N parallel IDEA tasks, spawn N distinct team-worker agents named ideator-1, ideator-2, etc.

Agent({
  subagent_type: "team-worker",
  name: "ideator-<N>",
  team_name: "brainstorm",
  run_in_background: true,
  prompt: `## Role Assignment
role: ideator
role_spec: <skill_root>/roles/ideator/role.md
session: <session-folder>
session_id: <session-id>
team_name: brainstorm
requirement: <topic-description>
agent_name: ideator-<N>
inner_loop: false

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/ideator/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery, owner=ideator-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).`
})

User Commands

CommandAction
check / statusView execution status graph, no advancement
resume / continueCheck worker states, advance next step

Session Directory

.workflow/.team/BRS-<slug>-<date>/
├── session.json                    # Session metadata + pipeline + gc_round
├── task-analysis.json              # Coordinator analyze output
├── .msg/
│   ├── messages.jsonl              # Message bus log
│   └── meta.json                   # Session state + cross-role state
├── wisdom/                         # Cross-task knowledge
│   ├── learnings.md
│   ├── decisions.md
│   ├── conventions.md
│   └── issues.md
├── ideas/                          # Ideator output
│   ├── idea-001.md
│   └── idea-002.md
├── critiques/                      # Challenger output
│   ├── critique-001.md
│   └── critique-002.md
├── synthesis/                      # Synthesizer output
│   └── synthesis-001.md
└── evaluation/                     # Evaluator output
    └── evaluation-001.md

Specs Reference

Error Handling

ScenarioResolution
Unknown commandError with available command list
Role not foundError with role registry
CLI tool failsWorker fallback to direct implementation
Fast-advance conflictCoordinator reconciles on next callback
Completion action failsDefault to Keep Active
Generator-Critic loop exceeds 2 roundsForce convergence to synthesizer
No ideas generatedCoordinator prompts with seed questions

Comments

Markdown supported