Engineering Advanced AgentsWorkflowsPatterns

Agent Workflow Designer

Sequential, parallel, router, orchestrator, and evaluator agent patterns.

Install for

Real Conversations

See how the Agent Workflow Designer skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

I need to research 8 competitors simultaneously and produce a synthesis report. Right now I'm doing them sequentially and it takes 4 minutes. Can I parallelize this with Claude?

Agent

Yes — this is the canonical parallel fan-out/fan-in use case. Sequential = 8 × 30s = 4 min. Parallel = 30s total.

import asyncio
import anthropic

async def research_competitor(client, name: str) -> dict:
    loop = asyncio.get_event_loop()
    resp = await loop.run_in_executor(None, lambda: client.messages.create(
        model="claude-3-5-sonnet-20241022",
        max_tokens=1024,
        system="Competitive intelligence analyst. Return: pricing, key features, weaknesses, target market.",
        messages=[{"role": "user", "content": f"Analyze {name} for a project management SaaS comparison."}]
    ))
    return {"name": name, "analysis": resp.content[0].text,
            "tokens": resp.usage.input_tokens + resp.usage.output_tokens}

async def run_research(competitors: list[str]) -> str:
    client = anthropic.Anthropic()
    results = await asyncio.gather(
        *[research_competitor(client, c) for c in competitors],
        return_exceptions=True
    )
    successful = [r for r in results if not isinstance(r, Exception)]
    combined = "\n\n".join(f"## {r['name']}\n{r['analysis']}" for r in successful)
    synthesis = client.messages.create(
        model="claude-3-5-sonnet-20241022", max_tokens=2048,
        system="Strategic analyst. Produce a comparison matrix and top 3 strategic recommendations.",
        messages=[{"role": "user", "content": combined}]
    )
    return synthesis.content[0].text

Cost note: 8 parallel Sonnet calls ≈ $0.08 total. Each research agent gets max 1,024 output tokens to keep the fan-in prompt manageable.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best
Claude Opus 4.8 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2
Good
Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only
32K+ Skill + conversation
100K+ Skill + references + codebase

All current frontier models support 100K+ context.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Agent Workflow Designer?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

Install for

← Browse all skills