agent-workflow-designer

What this skill does

# Agent Workflow Designer

**Tier:** POWERFUL  
**Category:** Engineering  
**Domain:** Multi-Agent Systems / AI Orchestration

---

## Overview

Design production-grade multi-agent orchestration systems. Covers five core patterns (sequential pipeline, parallel fan-out/fan-in, hierarchical delegation, event-driven, consensus), platform-specific implementations, handoff protocols, state management, error recovery, context window budgeting, and cost optimization.

---

## Core Capabilities

- Pattern selection guide for any orchestration requirement
- Handoff protocol templates (structured context passing)
- State management patterns for multi-agent workflows
- Error recovery and retry strategies
- Context window budget management
- Cost optimization strategies per platform
- Platform-specific configs: Claude Code Agent Teams, OpenClaw, CrewAI, AutoGen

---

## When to Use

- Building a multi-step AI pipeline that exceeds one agent's context capacity
- Parallelizing research, generation, or analysis tasks for speed
- Creating specialist agents with defined roles and handoff contracts
- Designing fault-tolerant AI workflows for production

---

## Pattern Selection Guide

```
Is the task sequential (each step needs previous output)?
  YES → Sequential Pipeline
  NO  → Can tasks run in parallel?
          YES → Parallel Fan-out/Fan-in
          NO  → Is there a hierarchy of decisions?
                  YES → Hierarchical Delegation
                  NO  → Is it event-triggered?
                          YES → Event-Driven
                          NO  → Need consensus/validation?
                                  YES → Consensus Pattern
```

---

## Pattern 1: Sequential Pipeline

**Use when:** Each step depends on the previous output. Research → Draft → Review → Polish.

```python
# sequential_pipeline.py
from dataclasses import dataclass
from typing import Callable, Any
import anthropic

@dataclass
class PipelineStage:
    name: "str"
    system_prompt: str
    input_key: str      # what to take from state
    output_key: str     # what to write to state
    model: str = "claude-3-5-sonnet-20241022"
    max_tokens: int = 2048

class SequentialPipeline:
    def __init__(self, stages: list[PipelineStage]):
        self.stages = stages
        self.client = anthropic.Anthropic()
    
    def run(self, initial_input: str) -> dict:
        state = {"input": initial_input}
        
        for stage in self.stages:
            print(f"[{stage.name}] Processing...")
            
            stage_input = state.get(stage.input_key, "")
            
            response = self.client.messages.create(
                model=stage.model,
                max_tokens=stage.max_tokens,
                system=stage.system_prompt,
                messages=[{"role": "user", "content": stage_input}],
            )
            
            state[stage.output_key] = response.content[0].text
            state[f"{stage.name}_tokens"] = response.usage.input_tokens + response.usage.output_tokens
            
            print(f"[{stage.name}] Done. Tokens: {state[f'{stage.name}_tokens']}")
        
        return state

# Example: Blog post pipeline
pipeline = SequentialPipeline([
    PipelineStage(
        name="researcher",
        system_prompt="You are a research specialist. Given a topic, produce a structured research brief with: key facts, statistics, expert perspectives, and controversy points.",
        input_key="input",
        output_key="research",
    ),
    PipelineStage(
        name="writer",
        system_prompt="You are a senior content writer. Using the research provided, write a compelling 800-word blog post with a clear hook, 3 main sections, and a strong CTA.",
        input_key="research",
        output_key="draft",
    ),
    PipelineStage(
        name="editor",
        system_prompt="You are a copy editor. Review the draft for: clarity, flow, grammar, and SEO. Return the improved version only, no commentary.",
        input_key="draft",
        output_key="final",
    ),
])
```

---

## Pattern 2: Parallel Fan-out / Fan-in

**Use when:** Independent tasks that can run concurrently. Research 5 competitors simultaneously.

```python
# parallel_fanout.py
import asyncio
import anthropic
from typing import Any

async def run_agent(client, task_name: "str-system-str-user-str-model-str"claude-3-5-sonnet-20241022") -> dict:
    """Single async agent call"""
    loop = asyncio.get_event_loop()
    
    def _call():
        return client.messages.create(
            model=model,
            max_tokens=2048,
            system=system,
            messages=[{"role": "user", "content": user}],
        )
    
    response = await loop.run_in_executor(None, _call)
    return {
        "task": task_name,
        "output": response.content[0].text,
        "tokens": response.usage.input_tokens + response.usage.output_tokens,
    }

async def parallel_research(competitors: list[str], research_type: str) -> dict:
    """Fan-out: research all competitors in parallel. Fan-in: synthesize results."""
    client = anthropic.Anthropic()
    
    # FAN-OUT: spawn parallel agent calls
    tasks = [
        run_agent(
            client,
            task_name=competitor,
            system=f"You are a competitive intelligence analyst. Research {competitor} and provide: pricing, key features, target market, and known weaknesses.",
            user=f"Analyze {competitor} for comparison with our product in the {research_type} market.",
        )
        for competitor in competitors
    ]
    
    results = await asyncio.gather(*tasks, return_exceptions=True)
    
    # Handle failures gracefully
    successful = [r for r in results if not isinstance(r, Exception)]
    failed = [r for r in results if isinstance(r, Exception)]
    
    if failed:
        print(f"Warning: {len(failed)} research tasks failed: {failed}")
    
    # FAN-IN: synthesize
    combined_research = "\n\n".join([
        f"## {r['task']}\n{r['output']}" for r in successful
    ])
    
    synthesis = await run_agent(
        client,
        task_name="synthesizer",
        system="You are a strategic analyst. Synthesize competitor research into a concise comparison matrix and strategic recommendations.",
        user=f"Synthesize these competitor analyses:\n\n{combined_research}",
        model="claude-3-5-sonnet-20241022",
    )
    
    return {
        "individual_analyses": successful,
        "synthesis": synthesis["output"],
        "total_tokens": sum(r["tokens"] for r in successful) + synthesis["tokens"],
    }
```

---

## Pattern 3: Hierarchical Delegation

**Use when:** Complex tasks with subtask discovery. Orchestrator breaks down work, delegates to specialists.

```python
# hierarchical_delegation.py
import json
import anthropic

ORCHESTRATOR_SYSTEM = """You are an orchestration agent. Your job is to:
1. Analyze the user's request
2. Break it into subtasks
3. Assign each to the appropriate specialist agent
4. Collect results and synthesize

Available specialists:
- researcher: finds facts, data, and information
- writer: creates content and documents  
- coder: writes and reviews code
- analyst: analyzes data and produces insights

Respond with a JSON plan:
{
  "subtasks": [
    {"id": "1", "agent": "researcher", "task": "...", "depends_on": []},
    {"id": "2", "agent": "writer", "task": "...", "depends_on": ["1"]}
  ]
}"""

SPECIALIST_SYSTEMS = {
    "researcher": "You are a research specialist. Find accurate, relevant information and cite sources when possible.",
    "writer": "You are a professional writer. Create clear, engaging content in the requested format.",
    "coder": "You are a senior software engineer. Write clean, well-commented code with error handling.",
    "analyst": "You are a data analyst. Provide structured analysis with evidence-backed conclusions.",
}

class HierarchicalOrchestrator:
    def __init__(self):
        self.client = anthropic.Anthropic()
    
    def run(se