Spawn and coordinate team-agents and orchestration patterns for parallel execution. Use for complex multi-component work.
Spawns specialized agents for parallel execution of complex multi-component work. Triggers when requirements need decomposition, architectural decisions, or independent tasks can run concurrently.
/plugin marketplace add duyet/claude-plugins/plugin install duyetbot@duyet-claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Duyetbot's capability to spawn and coordinate other agents for parallel execution.
From @team-agents plugin:
| Agent | Model | Use For |
|---|---|---|
leader | opus | Complex decomposition, team coordination |
senior-engineer | sonnet | Architectural decisions, complex impl |
junior-engineer | haiku | Clear specs, fast execution |
From @orchestration plugin:
Launch independent agents simultaneously:
├── Agent 1: Task A
├── Agent 2: Task B
└── Agent 3: Task C
→ All run in parallel
Sequential stages:
Stage 1 → Stage 2 → Stage 3
(each depends on previous)
Distribute then aggregate:
Map: Split work across agents
Reduce: Synthesize results
Competing approaches:
├── Hypothesis A
├── Hypothesis B
└── Hypothesis C
→ Select best evidence-backed
[ANALYZE] Is this parallelizable?
- Independent components? → Fan-out
- Sequential dependencies? → Pipeline
- Need decomposition? → Spawn @leader
[SELECT] Match agent to task:
- Complex/architectural → @senior-engineer
- Clear/straightforward → @junior-engineer
- Need coordination → @leader
Task tool with run_in_background=True:
=== WORKER AGENT ===
You are a WORKER spawned by duyetbot.
========================
TASK: [specific assignment]
CONTEXT: [background info]
SCOPE: [boundaries]
OUTPUT: [expected deliverable]
[MONITOR] Track agent progress
[WAIT] Await completion
[VERIFY] Check quality gates
[INTEGRATE] Combine results
[1] ANALYZE → 3 independent components identified
[2] SPAWN @senior-engineer → "Component A"
[3] SPAWN @junior-engineer → "Component B"
[4] SPAWN @junior-engineer → "Component C"
[5] WAIT → All agents complete
[6] VERIFY → Integration tests pass
─── duyetbot ── coordinating ─────
Before accepting agent output:
BAD: Spawn 5 agents for a simple fix
GOOD: Solo execution for simple tasks
BAD: "Fix the bug"
GOOD: "Fix auth timeout in auth.ts:45, add retry logic with 3 attempts"
BAD: Spawn parallel agents for dependent tasks
GOOD: Pipeline pattern for sequential dependencies
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.