create-workflow

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

create-workflow

Turn a short natural-language test description into a new getlark workflow. The user supplies the description (target + steps). This skill derives a concise workflow name, surfaces optional settings (mode, secret contexts, group), and calls

getlark workflows create

getlark workflows can test any surface — web UIs, HTTP/GraphQL APIs, CLIs, shell scripts, data pipelines, or mixed flows. Do not assume the target is a browser URL.

将简短的自然语言测试描述转换为新的getlark工作流。用户需提供测试描述（包含测试目标+步骤）。本技能会生成简洁的工作流名称，展示可选配置（模式、密钥上下文、分组），并调用

getlark workflows create

命令。

getlark工作流可测试任意载体——Web界面、HTTP/GraphQL API、CLI、Shell脚本、数据管道或混合流程。请勿默认测试目标为浏览器URL。

Inputs

输入参数

Description (required) — free-form text containing a target (URL, API base, CLI binary, script path, etc.) and ordered steps. Examples:
- Browser: "Go to https://app.example.com/login, sign in with the
```
staging
```
  credentials, click 'New project', confirm the modal, assert dashboard loads."
- API: "POST https://api.acme.test/v1/orders with
```
staging_api
```
  creds and a sample cart payload, assert 201 and that the response
```
order.status
```
  is
```
pending
```
  ."
- CLI: "Run
```
mytool import ./fixtures/sample.csv --dry-run
```
  , assert exit code 0 and stdout contains
```
3 rows parsed
```
  ."

If the user invoked

/getlark:create-workflow <text>

, treat

<text>

as the description. Otherwise ask for it.

描述（必填）——包含测试目标（URL、API基准地址、CLI二进制文件、脚本路径等）和有序步骤的自由格式文本。示例：
- 浏览器测试："访问https://app.example.com/login，使用`staging`凭据登录，点击“新建项目”，确认弹窗出现，验证仪表盘加载完成。"
- API测试："使用
```
staging_api
```
  凭据和示例购物车负载向https://api.acme.test/v1/orders发送POST请求，验证返回状态码为201且响应中的`order.status`为`pending`。"
- CLI测试："运行
```
mytool import ./fixtures/sample.csv --dry-run
```
  ，验证退出码为0且标准输出包含
```
3 rows parsed
```
  。"

若用户执行

/getlark:create-workflow <text>

命令，则将

<text>

视为测试描述。否则需向用户询问测试描述。

Procedure

操作流程

Step 1 — Collect / confirm the description

步骤1 — 收集/确认测试描述

Ensure the description contains a target (URL, API endpoint, CLI command, script path, etc.) and at least one action step. If either is missing, ask one targeted follow-up. Do not pad thin descriptions with invented steps — confirm with the user first.

确保测试描述包含测试目标（URL、API端点、CLI命令、脚本路径等）和至少一个操作步骤。若缺少任意一项，需针对性地向用户追问一次。请勿自行补充内容单薄的描述，需先与用户确认。

Step 2 — Derive a name

步骤2 — 生成工作流名称

Generate a short, Title-Case name (3–6 words) that captures the intent. Heuristic:

Start from the primary verb + object in the description ("Sign In Flow", "Guest Checkout", "Create New Project").
Keep under ~50 characters.
Avoid URL fragments, credentials, or timestamps.

Show the derived name to the user before creating. Offer to accept or override.

生成一个简短的标题格式名称（3-6个单词），准确体现测试意图。参考规则：

从描述中的核心动词+对象入手（如“登录流程”、“访客结账”、“创建新项目”）。
长度控制在约50字符以内。
避免包含URL片段、凭据或时间戳。

在创建工作流前，需将生成的名称展示给用户，提供确认或修改的选项。

Step 3 — Ask about optional fields (only if relevant)

步骤3 — 询问可选配置（仅在相关时）

Ask only the questions that matter for this workflow. Skip the rest.

Mode — default
```
ai_driven
```
. Only ask if the user mentioned "deterministic", "scripted", "locked", or similar.
Secret contexts — ask if the description references credentials, API tokens, or anything named in quotes that looks like a context (e.g., "the
```
staging
```
credentials"). Offer to list existing contexts via
```
getlark secret-contexts list
```
.
Group — ask if the user has mentioned organizing tests, or if
```
getlark workflow-groups list
```
has existing groups. Otherwise skip.

Use AskUserQuestion for a single batched prompt when more than one optional field is in play.

仅询问与当前工作流相关的配置问题，其余跳过。

模式——默认值为
```
ai_driven
```
。仅当用户提及“确定性”、“脚本化”、“锁定”等类似词汇时才询问。
密钥上下文——若描述中提及凭据、API令牌或任何带引号的疑似上下文名称（如“
```
staging
```
凭据”），则询问用户。可通过
```
getlark secret-contexts list
```
命令列出现有上下文供用户参考。
分组——若用户提及需整理测试，或
```
getlark workflow-groups list
```
命令显示存在现有分组，则询问用户。否则跳过。

若存在多个需询问的可选配置，可通过AskUserQuestion工具一次性批量提问。

Step 4 — Invoke the CLI

步骤4 — 调用CLI命令

Build the command with properly quoted arguments:

bash

getlark workflows create \
  --name "<derived name>" \
  --description "<full description>" \
  [--mode deterministic] \
  [--secret-contexts name1 name2] \
  [--group-id <id>]

Description is passed verbatim — getlark's generation step parses the target and steps server-side. Do not restructure or bullet-ify it.

Note:

--secret-contexts

takes space-separated values (variadic), not comma-separated.

构建带有正确引号参数的命令：

bash

getlark workflows create \
  --name "<生成的名称>" \
  --description "<完整测试描述>" \
  [--mode deterministic] \
  [--secret-contexts name1 name2] \
  [--group-id <id>]

测试描述需原样传递——getlark的生成步骤会在服务器端解析测试目标和步骤。请勿重构或改为列表格式。

注意：

--secret-contexts

参数接受空格分隔的多个值（可变参数），而非逗号分隔。

Step 5 — Report result

步骤5 — 反馈结果

The CLI prints the new workflow JSON to stdout. Extract and report:

Workflow
```
id
```
```
status
```
(will typically be
```
pending_generation
```
initially)

Link:

https://dashboard.getlark.ai/workflows/<id>

Tell the user the workflow is now queued for generation and suggest they run

/getlark:invoke-workflow

once the workflow status reaches

active

(or

generation_successful

). They can check status via

getlark workflows get <id>

CLI命令会将新工作流的JSON信息输出到标准输出。需提取并反馈以下内容：

工作流
```
id
```
```
status
```
（初始状态通常为
```
pending_generation
```
）

链接：

https://dashboard.getlark.ai/workflows/<id>

告知用户工作流已进入生成队列，并建议当工作流状态变为

active

（或

generation_successful

）后，执行

/getlark:invoke-workflow

命令运行工作流。用户可通过

getlark workflows get <id>

命令查看工作流状态。

Failure modes

失败场景

--name
or
--description
missing: the CLI hard-errors. This skill must always supply both.
Unknown
--group-id
: verify with
```
getlark workflow-groups list
```
before passing.
Unknown
--secret-contexts
name: verify with
```
getlark secret-contexts list
```
. The API will reject unknown contexts.

缺少
--name
或
--description
参数：CLI命令会直接报错。本技能必须始终提供这两个参数。
未知
--group-id
：传递前需通过
```
getlark workflow-groups list
```
命令验证。
未知
--secret-contexts
名称：需通过
```
getlark secret-contexts list
```
命令验证。API会拒绝未知的上下文名称。

Example

示例

User says:

/getlark:create-workflow Go to https://app.example.com/signup, fill the form with a new email, submit, verify confirmation email message appears.

Derive: name = "Signup Flow Confirmation"

Run:

bash

getlark workflows create \
  --name "Signup Flow Confirmation" \
  --description "Go to https://app.example.com/signup, fill the form with a new email, submit, verify confirmation email message appears."

Report id + dashboard link.

用户输入：

/getlark:create-workflow 访问https://app.example.com/signup，使用新邮箱填写表单，提交，验证确认邮件提示出现。

生成名称："Signup Flow Confirmation"

执行命令：

bash

getlark workflows create \
  --name "Signup Flow Confirmation" \
  --description "访问https://app.example.com/signup，使用新邮箱填写表单，提交，验证确认邮件提示出现。"

反馈工作流ID和仪表盘链接。