workflow-builder

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Workflow Builder

工作流构建器（Workflow Builder）

Create and execute custom, repeatable multi-step AI workflows. Each step can use a different model, and independent steps run in parallel waves.

创建并执行自定义、可重复的多步骤AI工作流。每个步骤可使用不同的模型，独立步骤会以并行批次运行。

Capabilities

功能

This skill has two modes:

Mode	When to use	Reference
Plan	User wants to create or design a new workflow	`references/plan.md`
Run	User wants to execute, resume, or re-run a workflow	`references/run.md`

此Skill包含两种模式：

模式	使用场景	参考文档
规划（Plan）	用户想要创建或设计新工作流	`references/plan.md`
运行（Run）	用户想要执行、恢复或重新运行工作流	`references/run.md`

Quick Start

快速开始

Create: "Create a workflow called dependency-cleanup"
Run: "Run the dependency-cleanup workflow"
Resume: "Resume the dependency-cleanup workflow"

创建：“创建名为dependency-cleanup的工作流”
运行：“运行dependency-cleanup工作流”
恢复：“恢复dependency-cleanup工作流”

Routing

路由逻辑

Determine the user's intent from their message or

$ARGUMENTS

If the user says "create", "plan", "design", or "new workflow" → Read and follow
```
references/plan.md
```
If the user says "run", "execute", "start", or "resume" → Read and follow
```
references/run.md
```
If
```
$ARGUMENTS
```
starts with
```
plan
```
→ Read and follow
```
references/plan.md
```
with the remaining argument as workflow name
If
```
$ARGUMENTS
```
starts with
```
run
```
→ Read and follow
```
references/run.md
```
with the remaining argument as workflow name
If unclear, ask the user: "Would you like to create a new workflow or run an existing one?"

根据用户消息或

$ARGUMENTS

判断用户意图：

如果用户提到“create”、“plan”、“design”或“new workflow” → 阅读并遵循
```
references/plan.md
```
的指引
如果用户提到“run”、“execute”、“start”或“resume” → 阅读并遵循
```
references/run.md
```
的指引
如果
```
$ARGUMENTS
```
以
```
plan
```
开头 → 阅读并遵循
```
references/plan.md
```
，剩余参数作为工作流名称
如果
```
$ARGUMENTS
```
以
```
run
```
开头 → 阅读并遵循
```
references/run.md
```
，剩余参数作为工作流名称
如果意图不明确，询问用户： “您想要创建新工作流还是运行现有工作流？”

Workflow Structure

工作流结构

A workflow is a directory at

.somnio/workflows/<name>/

containing:

.somnio/workflows/<name>/
├── context.md              — Manifest with step list and metadata
├── 01-<step-name>.md       — Step 1 prompt
├── 02-<step-name>.md       — Step 2 prompt
├── ...
├── config.claudecode.json  — Model assignments (optional)
├── progress.json           — Execution state (auto-generated)
└── outputs/                — Step output files (auto-generated)

工作流是位于

.somnio/workflows/<name>/

目录下的一组文件，结构如下：

.somnio/workflows/<name>/
├── context.md              — 包含步骤列表和元数据的清单文件
├── 01-<step-name>.md       — 步骤1的提示词文件
├── 02-<step-name>.md       — 步骤2的提示词文件
├── ...
├── config.claudecode.json  — 模型分配配置（可选）
├── progress.json           — 执行状态文件（自动生成）
└── outputs/                — 步骤输出文件目录（自动生成）

Key Concepts

核心概念

Steps run in fresh AI contexts (separate subagents)
Tags (
```
research
```
,
```
planning
```
,
```
execution
```
) map to model assignments
Dependencies (
```
needs
```
) determine parallel wave grouping
Placeholders (
```
{output_path}
```
,
```
{step_N_output}
```
) enable data flow between steps
Independent steps with no
```
needs
```
run concurrently in the same wave

步骤（Steps）：在全新的AI上下文（独立子Agent）中运行
标签（Tags）（
```
research
```
、
```
planning
```
、
```
execution
```
）：与模型分配关联
依赖关系（Dependencies）（
```
needs
```
）：决定并行批次的分组
占位符（Placeholders）（
```
{output_path}
```
、
```
{step_N_output}
```
）：实现步骤间的数据流转
无
```
needs
```
依赖的独立步骤会在同一批次中并发运行