ホーム/AI 工程/create-workflow
C

create-workflow

by @vapiaiv
4.9(12)

Vapiプラットフォームで視覚的な会話ワークフローを構築し、ドラッグ&ドロップノードを通じて複雑なインタラクションロジックを設計し、AI会話の自動化とインテリジェント化を実現します。

AI Workflow AutomationProcess OrchestrationVAPIAI EngineeringBusiness Process AutomationGitHub
インストール方法
npx skills add vapiai/skills --skill create-workflow
compare_arrows

Before / After 効果比較

1
使用前

複雑な音声会話フローを構築するには、大量のコードロジックと条件判断が必要であり、特に多段階、多分岐のインタラクションシナリオでは、直感的に理解し維持することが困難です。

使用後

create-workflowスキルを使用することで、視覚的なノードを通じて会話フローを構築し、ツール実行、条件分岐、ハンドオフを実現できます。これにより、音声アシスタントの開発と管理が大幅に簡素化され、可読性と保守性が向上します。

description SKILL.md


name: create-workflow description: Build visual conversation workflows in Vapi with nodes for conversation steps, tool execution, conditional branching, and handoffs. Use when creating structured multi-step voice interactions that need deterministic flow control beyond what a single assistant prompt provides. license: MIT compatibility: Requires internet access and a Vapi API key (VAPI_API_KEY). metadata: author: vapi version: "1.0"

Vapi Workflow Creation

Build structured conversation workflows with visual node-based flows. Workflows provide deterministic control over conversation steps, branching logic, and tool execution.

Setup: Ensure VAPI_API_KEY is set. See the setup-api-key skill if needed.

When to Use Workflows vs Assistants

FeatureAssistantWorkflow
Simple conversationsBest choiceOver-engineered
Multi-step processesCan work with good promptingBest choice
Deterministic flowHard to guaranteeBuilt-in
Conditional branchingPrompt-dependentVisual nodes
Complex state managementDifficultNative support

Quick Start

Workflows are best built in the Vapi Dashboard visual editor at https://dashboard.vapi.ai — but they can also be configured via API.

Dashboard Workflow

  1. Go to https://dashboard.vapi.ai
  2. Navigate to Workflows
  3. Click Create Workflow
  4. Add nodes: Conversation, Tool, Condition, Handoff
  5. Connect nodes to define the flow
  6. Publish and attach to a phone number or call

Using a Workflow in a Call

curl -X POST https://api.vapi.ai/call \
  -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflowId": "your-workflow-id",
    "phoneNumberId": "your-phone-number-id",
    "customer": {
      "number": "+11234567890"
    }
  }'

Node Types

Conversation Node

The core building block — the assistant has a conversation within defined boundaries:

  • System prompt specific to this step
  • Model and voice configuration
  • Exit conditions that trigger transitions to other nodes
  • Variables to extract and pass between nodes

Tool Node

Execute a tool (API call, function) and use the result in subsequent nodes.

Condition Node

Branch the flow based on variables or conversation state.

Handoff Node

Transfer to another workflow, assistant, or phone number.

Workflow Patterns

Appointment Scheduling Flow

[Greeting] → [Collect Date] → [Check Availability (Tool)] → [Confirm Booking] → [Goodbye]
                                         ↓ (unavailable)
                                 [Suggest Alternatives] → [Confirm Booking]

Lead Qualification Flow

[Introduction] → [Ask Budget] → [Ask Timeline] → [Qualify (Condition)]
                                                        ↓ (qualified)
                                                  [Schedule Demo]
                                                        ↓ (not qualified)
                                                  [Send Resources]

Support Triage Flow

[Greeting] → [Identify Issue (Condition)]
                  ↓ (billing)        ↓ (technical)        ↓ (other)
            [Billing Flow]    [Tech Support Flow]    [General Help]

Attaching Workflows

To a Phone Number

curl -X PATCH https://api.vapi.ai/phone-number/{id} \
  -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflowId": "your-workflow-id"
  }'

In an Outbound Call

curl -X POST https://api.vapi.ai/call \
  -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflowId": "your-workflow-id",
    "phoneNumberId": "your-phone-number-id",
    "customer": { "number": "+11234567890" }
  }'

References

Additional Resources

This skills repository includes a Vapi documentation MCP server (vapi-docs) that gives your AI agent access to the full Vapi knowledge base. Use the searchDocs tool to look up anything beyond what this skill covers — advanced configuration, troubleshooting, SDK details, and more.

Auto-configured: If you cloned or installed these skills, the MCP server is already configured via .mcp.json (Claude Code), .cursor/mcp.json (Cursor), or .vscode/mcp.json (VS Code Copilot).

Manual setup: If your agent doesn't auto-detect the config, run:

claude mcp add vapi-docs -- npx -y mcp-remote https://docs.vapi.ai/_mcp/server

See the README for full setup instructions across all supported agents.

forumユーザーレビュー (0)

レビューを書く

効果
使いやすさ
ドキュメント
互換性

レビューなし

統計データ

インストール数316
評価4.9 / 5.0
バージョン
更新日2026年3月17日
比較事例1 件

ユーザー評価

4.9(12)
5
0%
4
0%
3
0%
2
0%
1
0%

この Skill を評価

0.0

対応プラットフォーム

🔧Claude Code
🔧OpenClaw
🔧OpenCode
🔧Codex
🔧Gemini CLI
🔧GitHub Copilot
🔧Amp
🔧Kimi CLI

タイムライン

作成2026年3月17日
最終更新2026年3月17日