Team Motion Design

Team Motion Design

Systematic motion design pipeline: research -> choreography -> animation -> performance testing. Built on team-worker agent architecture -- all worker roles share a single agent definition with role-specific Phase 2-4 loaded from roles/<role>/role.md.

Architecture

Skill(skill="team-motion-design", args="task 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
           [team-worker agents, each loads roles/<role>/role.md]
      motion-researcher  choreographer  animator  motion-tester

Role Registry

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

Delegation Lock

Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.

Before calling ANY tool, apply this check:

If a tool call is BLOCKED: STOP. Create a task, spawn a worker.

No exceptions for "simple" tasks. Even a single-file read-and-report MUST go through spawn_agent.

Shared Constants

• Session prefix: MD
• Session path: .workflow/.team/MD-<date>-<slug>/
• CLI tools: ccw cli --mode analysis (read-only), ccw cli --mode write (modifications)
• Message bus: mcp__ccw-tools__team_msg(session_id=<session-id>, ...)
• Max GC rounds: 2

Worker Spawn Template

Coordinator spawns workers using this template:

spawn_agent({
  agent_type: "team_worker",
  task_name: "<task-id>",
  fork_turns: "none",
  message: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
requirement: <task-description>
inner_loop: <true|false>

Read role_spec file (<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.

## Task Context
task_id: <task-id>
title: <task-title>
description: <task-description>
pipeline_phase: <pipeline-phase>

## Upstream Context
<prev_context>`
})

After spawning, use wait_agent({ timeout_ms: 1800000 }) to collect results. If result.timed_out, send STATUS_CHECK via followup_task (wait 3 min), then FINALIZE with interrupt (wait 3 min), then mark timed_out and close agents. Use close_agent({ target }) each worker.

Model Selection Guide

Motion design is a performance-critical pipeline where research informs choreography decisions and animations must pass strict GPU performance gates. Researcher needs thorough profiling, animator needs creative implementation with inner loop capability.

Research-to-Choreography Context Flow

Researcher findings must reach choreographer via coordinator's upstream context:

// After MRESEARCH-001 completes, coordinator sends findings to choreographer
spawn_agent({
  agent_type: "team_worker",
  task_name: "CHOREO-001",
  fork_turns: "none",
  message: `## Upstream Context
Research findings: <session>/research/animation-inventory.json
Performance baseline: <session>/research/performance-baseline.json
Easing catalog: <session>/research/easing-catalog.json`
})

User Commands

Specs Reference

• specs/pipelines.md -- Pipeline definitions and task registry
• specs/motion-tokens.md -- Animation token schema
• specs/gpu-constraints.md -- Compositor-only animation rules
• specs/reduced-motion.md -- Accessibility motion preferences

Session Directory

.workflow/.team/MD-<date>-<slug>/
+-- .msg/
|   +-- messages.jsonl         # Team message bus
|   +-- meta.json              # Pipeline config + GC state
+-- research/                  # Motion researcher output
|   +-- perf-traces/           # Chrome DevTools performance traces
|   +-- animation-inventory.json
|   +-- performance-baseline.json
|   +-- easing-catalog.json
+-- choreography/              # Choreographer output
|   +-- motion-tokens.json
|   +-- sequences/             # Scroll choreography sequences
+-- animations/                # Animator output
|   +-- keyframes/             # CSS @keyframes files
|   +-- orchestrators/         # JS animation orchestrators
+-- testing/                   # Motion tester output
|   +-- traces/                # Performance trace data
|   +-- reports/               # Performance reports
+-- wisdom/                    # Cross-task knowledge

v4 Agent Coordination

Message Semantics

Agent Health Check

Use list_agents({}) in handleResume and handleComplete:

// Reconcile session state with actual running agents
const running = list_agents({})
// Compare with tasks.json active_agents
// Reset orphaned tasks (in_progress but agent gone) to pending

Named Agent Targeting

Workers are spawned with task_name: "<task-id>" enabling direct addressing:

• send_message({ target: "CHOREO-001", message: "..." }) -- send additional research findings to choreographer
• followup_task({ target: "ANIM-001", message: "..." }) -- assign animation from reviewed choreography specs
• close_agent({ target: "MTEST-001" }) -- cleanup after performance test

Error Handling