Agent Workflow Designer
- 614 installs
- 23.5k repo stars
- Updated July 17, 2026
- alirezarezvani/claude-skills
agent-workflow-designer is a Claude Code skill that generates reusable JSON workflow pattern templates so developers can orchestrate sequential, parallel, router, and orchestrator multi-agent steps in Claude, Cursor, or
About
agent-workflow-designer is an AI agent building skill from alirezarezvani/claude-skills that emits structured workflow pattern templates for coding agents. Each template encodes one of four orchestration models—sequential step chains, parallel fan-out and fan-in, intent-based routers with fallback handlers, and dynamic orchestrators with dependency management—using JSON fields like steps, fan_out, routes, and router. Developers reach for agent-workflow-designer when wiring multi-step agent pipelines in Claude Code, Cursor, or Codex and need a repeatable pattern instead of ad-hoc prompt chains. The readme documents four core patterns with copy-paste JSON examples, making the skill a blueprint library for agent orchestration rather than a runtime executor.
- 5 ready-to-use workflow pattern templates: Sequential, Parallel, Router, Orchestrator, Evaluator
- Includes pattern selection heuristics based on dependency shape, throughput needs, and quality gates
- Standardized handoff contract with workflow_id, step_id, task, constraints, upstream_artifacts and budget_tokens
- JSON-first templates that drop directly into agent orchestration loops
- Works before any creative or implementation work to reduce slop and token waste
Agent Workflow Designer by the numbers
- 614 all-time installs (skills.sh)
- Ranked #1,549 of 16,565 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 31, 2026 (Skillselion catalog sync)
npx skills add https://github.com/alirezarezvani/claude-skills --skill agent-workflow-designerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 614 |
|---|---|
| repo stars | ★ 23.5k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 17, 2026 |
| Repository | alirezarezvani/claude-skills ↗ |
How do you design multi-agent workflow patterns for coding agents?
Generate reusable workflow pattern templates that tell Claude, Cursor or Codex exactly how to orchestrate multiple agent steps.
Who is it for?
Developers building multi-step agent pipelines in Claude Code, Cursor, or Codex who need standardized orchestration blueprints.
Skip if: Developers who only need a single one-shot prompt or already run a dedicated workflow engine like Temporal or LangGraph.
When should I use this skill?
A developer asks to design, template, or structure multi-agent workflows with routing, parallelism, or orchestration steps.
What you get
Reusable JSON workflow pattern templates with sequential, parallel, router, and orchestrator step definitions
- JSON workflow pattern templates
- Multi-agent orchestration blueprints
By the numbers
- Documents 4 core workflow patterns: sequential, parallel, router, and orchestrator
Files
Agent Workflow Designer
Tier: POWERFUL Category: Engineering Domain: Multi-Agent Systems / AI Orchestration
---
Overview
Design production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls.
Core Capabilities
- Workflow pattern selection for multi-step agent systems
- Skeleton config generation for fast workflow bootstrapping
- Context and cost discipline across long-running flows
- Error recovery and retry strategy scaffolding
- Documentation pointers for operational pattern tradeoffs
---
When to Use
- A single prompt is insufficient for task complexity
- You need specialist agents with explicit boundaries
- You want deterministic workflow structure before implementation
- You need validation loops for quality or safety gates
---
Quick Start
# Generate a sequential workflow skeleton
python3 scripts/workflow_scaffolder.py sequential --name content-pipeline
# Generate an orchestrator workflow and save it
python3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json---
Pattern Map
sequential: strict step-by-step dependency chainparallel: fan-out/fan-in for independent subtasksrouter: dispatch by intent/type with fallbackorchestrator: planner coordinates specialists with dependenciesevaluator: generator + quality gate loop
Detailed templates: references/workflow-patterns.md
---
Recommended Workflow
1. Select pattern based on dependency shape and risk profile. 2. Scaffold config via scripts/workflow_scaffolder.py. 3. Define handoff contract fields for every edge. 4. Add retry/timeouts and output validation gates. 5. Dry-run with small context budgets before scaling.
---
Common Pitfalls
- Over-orchestrating tasks solvable by one well-structured prompt
- Missing timeout/retry policies for external-model calls
- Passing full upstream context instead of targeted artifacts
- Ignoring per-step cost accumulation
Best Practices
1. Start with the smallest pattern that can satisfy requirements. 2. Keep handoff payloads explicit and bounded. 3. Validate intermediate outputs before fan-in synthesis. 4. Enforce budget and timeout limits in every step.
Workflow Pattern Templates
Sequential
Use when each step depends on prior output.
{
"pattern": "sequential",
"steps": ["research", "draft", "review"]
}Parallel
Use when independent tasks can fan out and then fan in.
{
"pattern": "parallel",
"fan_out": ["task_a", "task_b", "task_c"],
"fan_in": "synthesizer"
}Router
Use when tasks must be routed to specialized handlers by intent.
{
"pattern": "router",
"router": "intent_router",
"routes": ["sales", "support", "engineering"],
"fallback": "generalist"
}Orchestrator
Use when dynamic planning and dependency management are required.
{
"pattern": "orchestrator",
"orchestrator": "planner",
"specialists": ["researcher", "analyst", "coder"],
"dependency_mode": "dag"
}Evaluator
Use when output quality gates are mandatory before finalization.
{
"pattern": "evaluator",
"generator": "content_agent",
"evaluator": "quality_agent",
"max_iterations": 3,
"pass_threshold": 0.8
}Pattern Selection Heuristics
- Choose
sequentialfor strict linear workflows. - Choose
parallelfor throughput and latency reduction. - Choose
routerfor intent- or type-based branching. - Choose
orchestratorfor complex adaptive workflows. - Choose
evaluatorwhen correctness/quality loops are required.
Handoff Minimum Contract
workflow_idstep_idtaskconstraintsupstream_artifactsbudget_tokenstimeout_seconds
#!/usr/bin/env python3
"""Generate workflow skeleton configs from common multi-agent patterns."""
from __future__ import annotations
import argparse
import json
from pathlib import Path
from typing import Dict, List
def sequential_template(name: str) -> Dict:
return {
"name": name,
"pattern": "sequential",
"steps": [
{"id": "research", "agent": "researcher", "next": "draft"},
{"id": "draft", "agent": "writer", "next": "review"},
{"id": "review", "agent": "reviewer", "next": None},
],
"retry": {"max_attempts": 2, "backoff_seconds": 2},
}
def parallel_template(name: str) -> Dict:
return {
"name": name,
"pattern": "parallel",
"fan_out": {
"tasks": ["research_a", "research_b", "research_c"],
"agent": "analyst",
},
"fan_in": {"agent": "synthesizer", "output": "combined_report"},
"timeouts": {"per_task_seconds": 180, "fan_in_seconds": 120},
}
def router_template(name: str) -> Dict:
return {
"name": name,
"pattern": "router",
"router": {"agent": "router", "routes": ["sales", "support", "engineering"]},
"handlers": {
"sales": {"agent": "sales_specialist"},
"support": {"agent": "support_specialist"},
"engineering": {"agent": "engineering_specialist"},
},
"fallback": {"agent": "generalist"},
}
def orchestrator_template(name: str) -> Dict:
return {
"name": name,
"pattern": "orchestrator",
"orchestrator": {"agent": "orchestrator", "planning": "dynamic"},
"specialists": ["researcher", "coder", "analyst", "writer"],
"execution": {
"dependency_mode": "dag",
"max_parallel": 3,
"completion_policy": "all_required",
},
}
def evaluator_template(name: str) -> Dict:
return {
"name": name,
"pattern": "evaluator",
"generator": {"agent": "generator"},
"evaluator": {"agent": "evaluator", "criteria": ["accuracy", "format", "safety"]},
"loop": {
"max_iterations": 3,
"pass_threshold": 0.8,
"on_fail": "revise_and_retry",
},
}
PATTERNS = {
"sequential": sequential_template,
"parallel": parallel_template,
"router": router_template,
"orchestrator": orchestrator_template,
"evaluator": evaluator_template,
}
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Generate a workflow skeleton config from a pattern.")
parser.add_argument("pattern", choices=sorted(PATTERNS.keys()), help="Workflow pattern")
parser.add_argument("--name", default="new-workflow", help="Workflow name")
parser.add_argument("--output", help="Optional output path for JSON config")
return parser.parse_args()
def main() -> int:
args = parse_args()
config = PATTERNS[args.pattern](args.name)
payload = json.dumps(config, indent=2)
if args.output:
out = Path(args.output)
out.parent.mkdir(parents=True, exist_ok=True)
out.write_text(payload + "\n", encoding="utf-8")
print(f"Wrote workflow config to {out}")
else:
print(payload)
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8How it compares
Pick agent-workflow-designer over generic prompt skills when you need structured multi-agent orchestration blueprints instead of single-turn instructions.
FAQ
What workflow patterns does agent-workflow-designer support?
agent-workflow-designer supports four JSON workflow patterns: sequential for dependent step chains, parallel for fan-out and fan-in tasks, router for intent-based handler routing with fallback, and orchestrator for dynamic planning with dependency management.
Which coding agents work with agent-workflow-designer templates?
agent-workflow-designer templates target Claude, Cursor, and Codex coding agents. Each pattern is a reusable JSON blueprint developers paste into agent configuration to standardize multi-step orchestration.
Is Agent Workflow Designer safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.