agent-workflow-designer

# 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

```bash
# 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 chain
- `parallel`: fan-out/fan-in for independent subtasks
- `router`: dispatch by intent/type with fallback
- `orchestrator`: planner coordinates specialists with dependencies
- `evaluator`: 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.

{
  "format": "aiskill/v1",
  "skill": {
    "name": "agent-workflow-designer",
    "slug": "agent-workflow-designer",
    "version": "1.0.0",
    "description": "Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.",
    "category": "Development",
    "tags": [
      "ai-agents",
      "llm",
      "agents"
    ],
    "platforms": [
      "chatgpt",
      "claude-code",
      "cursor"
    ],
    "tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
    "license": "MIT"
  },
  "prompts": {
    "system": "# Agent Workflow Designer\r\n\r\n**Tier:** POWERFUL  \r\n**Category:** Engineering  \r\n**Domain:** Multi-Agent Systems / AI Orchestration\r\n\r\n---\r\n\r\n## Overview\r\n\r\nDesign production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls.\r\n\r\n## Core Capabilities\r\n\r\n- Workflow pattern selection for multi-step agent systems\r\n- Skeleton config generation for fast workflow bootstrapping\r\n- Context and cost discipline across long-running flows\r\n- Error recovery and retry strategy scaffolding\r\n- Documentation pointers for operational pattern tradeoffs\r\n\r\n---\r\n\r\n## When to Use\r\n\r\n- A single prompt is insufficient for task complexity\r\n- You need specialist agents with explicit boundaries\r\n- You want deterministic workflow structure before implementation\r\n- You need validation loops for quality or safety gates\r\n\r\n---\r\n\r\n## Quick Start\r\n\r\n```bash\r\n# Generate a sequential workflow skeleton\r\npython3 scripts/workflow_scaffolder.py sequential --name content-pipeline\r\n\r\n# Generate an orchestrator workflow and save it\r\npython3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json\r\n```\r\n\r\n---\r\n\r\n## Pattern Map\r\n\r\n- `sequential`: strict step-by-step dependency chain\r\n- `parallel`: fan-out/fan-in for independent subtasks\r\n- `router`: dispatch by intent/type with fallback\r\n- `orchestrator`: planner coordinates specialists with dependencies\r\n- `evaluator`: generator + quality gate loop\r\n\r\nDetailed templates: `references/workflow-patterns.md`\r\n\r\n---\r\n\r\n## Recommended Workflow\r\n\r\n1. Select pattern based on dependency shape and risk profile.\r\n2. Scaffold config via `scripts/workflow_scaffolder.py`.\r\n3. Define handoff contract fields for every edge.\r\n4. Add retry/timeouts and output validation gates.\r\n5. Dry-run with small context budgets before scaling.\r\n\r\n---\r\n\r\n## Common Pitfalls\r\n\r\n- Over-orchestrating tasks solvable by one well-structured prompt\r\n- Missing timeout/retry policies for external-model calls\r\n- Passing full upstream context instead of targeted artifacts\r\n- Ignoring per-step cost accumulation\r\n\r\n## Best Practices\r\n\r\n1. Start with the smallest pattern that can satisfy requirements.\r\n2. Keep handoff payloads explicit and bounded.\r\n3. Validate intermediate outputs before fan-in synthesis.\r\n4. Enforce budget and timeout limits in every step.",
    "user_template": ""
  },
  "variables": [],
  "install": {
    "steps": [
      {
        "title": "Download & unzip",
        "detail": "Download the .zip package from SkillVault and unzip it. The agent-workflow-designer/ folder contains SKILL.md plus any companion scripts, references and assets."
      },
      {
        "title": "Copy into your agent skills directory",
        "detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
      },
      {
        "title": "Use it",
        "detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
      }
    ]
  },
  "usage": {
    "steps": []
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/agent-workflow-designer",
    "exported_at": "2026-11-03T07:43:39.936Z"
  }
}

format: aiskill/v1
skill:
  name: agent-workflow-designer
  slug: agent-workflow-designer
  version: 1.0.0
  description: >-
    Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel,
    hierarchical), handoff contracts, failure handling, and cost/context controls. Use when
    architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent
    approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable
    handoffs.
  category: Development
  tags:
    - ai-agents
    - llm
    - agents
  platforms:
    - chatgpt
    - claude-code
    - cursor
  tested_environment: >-
    Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
    compatible agents
  license: MIT
prompts:
  system: "# Agent Workflow Designer\r\n\r\n**Tier:** POWERFUL  \r\n**Category:** Engineering  \r\n**Domain:** Multi-Agent Systems / AI Orchestration\r\n\r\n---\r\n\r\n## Overview\r\n\r\nDesign production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls.\r\n\r\n## Core Capabilities\r\n\r\n- Workflow pattern selection for multi-step agent systems\r\n- Skeleton config generation for fast workflow bootstrapping\r\n- Context and cost discipline across long-running flows\r\n- Error recovery and retry strategy scaffolding\r\n- Documentation pointers for operational pattern tradeoffs\r\n\r\n---\r\n\r\n## When to Use\r\n\r\n- A single prompt is insufficient for task complexity\r\n- You need specialist agents with explicit boundaries\r\n- You want deterministic workflow structure before implementation\r\n- You need validation loops for quality or safety gates\r\n\r\n---\r\n\r\n## Quick Start\r\n\r\n```bash\r\n# Generate a sequential workflow skeleton\r\npython3 scripts/workflow_scaffolder.py sequential --name content-pipeline\r\n\r\n# Generate an orchestrator workflow and save it\r\npython3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json\r\n```\r\n\r\n---\r\n\r\n## Pattern Map\r\n\r\n- `sequential`: strict step-by-step dependency chain\r\n- `parallel`: fan-out/fan-in for independent subtasks\r\n- `router`: dispatch by intent/type with fallback\r\n- `orchestrator`: planner coordinates specialists with dependencies\r\n- `evaluator`: generator + quality gate loop\r\n\r\nDetailed templates: `references/workflow-patterns.md`\r\n\r\n---\r\n\r\n## Recommended Workflow\r\n\r\n1. Select pattern based on dependency shape and risk profile.\r\n2. Scaffold config via `scripts/workflow_scaffolder.py`.\r\n3. Define handoff contract fields for every edge.\r\n4. Add retry/timeouts and output validation gates.\r\n5. Dry-run with small context budgets before scaling.\r\n\r\n---\r\n\r\n## Common Pitfalls\r\n\r\n- Over-orchestrating tasks solvable by one well-structured prompt\r\n- Missing timeout/retry policies for external-model calls\r\n- Passing full upstream context instead of targeted artifacts\r\n- Ignoring per-step cost accumulation\r\n\r\n## Best Practices\r\n\r\n1. Start with the smallest pattern that can satisfy requirements.\r\n2. Keep handoff payloads explicit and bounded.\r\n3. Validate intermediate outputs before fan-in synthesis.\r\n4. Enforce budget and timeout limits in every step."
  user_template: ""
variables: []
install:
  steps:
    - title: Download & unzip
      detail: >-
        Download the .zip package from SkillVault and unzip it. The agent-workflow-designer/ folder
        contains SKILL.md plus any companion scripts, references and assets.
    - title: Copy into your agent skills directory
      detail: >-
        Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
        .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
        reload the session.
    - title: Use it
      detail: >-
        Describe the task in natural language; the agent loads the skill automatically when the
        request matches the skill description.
usage:
  steps: []
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/agent-workflow-designer
  exported_at: "2026-11-03T07:43:39.936Z"