create-pipeline-v1

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Create Pipeline v1

创建Pipeline v1

Generate Harness v1 simplified Pipeline YAML and optionally push to Harness via MCP.

Alpha: This skill is currently in internal testing only.

生成Harness v1简化版Pipeline YAML，并可选择通过MCP推送到Harness。

Alpha阶段：本技能目前仅内部测试可用。

Instructions

操作说明

Confirm v1 format - User must specifically want v1 syntax. Default to v0 (
```
/create-pipeline
```
) if unclear.
Clarify requirements - Pipeline type (CI, CD, or both), language/framework, deployment target
Consult the spec reference - Use
```
references/v1-spec-schema.md
```
for the complete v1 schema, step types, action catalog, and examples

Select native actions - Always prefer native action and template steps over

run:

steps. Consult

references/native-actions.md

for the full mapping. Key rules:

Docker build/push → use

template: uses: buildAndPushToDocker

buildAndPushToECR

buildAndPushToGAR

(never

run: docker build && docker push

)

K8s deploy → use

action: uses: kubernetes-rolling-deploy

template: uses: k8sRollingDeployStep

(never

run: kubectl apply

)

Helm deploy → use

action: uses: helm-deploy

template: uses: helmDeployBasicStep

(never

run: helm upgrade --install

)

ECS deploy → use

template: uses: ecsBluegreenDeployStep

(never

run: aws ecs update-service

)

Terraform → use

template: uses: terraformStep

(never

run: terraform apply

)

Security scanning → use native STO templates (
```
gitleaksStep
```
,
```
banditStep
```
,
```
sbomOrchestrationStep
```
)

Uploads → use

template: uses: uploadArtifactsToS3

uploadArtifactsToGCS

(never

run: aws s3 cp

)

Approvals → use

approval: uses: harness

approval: uses: jira

(never polling scripts)

Ticketing → use

action: uses: jira-create

snow-create

(never

run: curl

)

HTTP requests → use

action: uses: http

template: uses: httpStep

(never

run: curl

)

Use
```
run:
```
steps only for custom build/test/lint commands with no native equivalent

Generate v1 YAML using flat structure,
```
${{ }}
```
expressions,
```
script
```
field for run steps, and
```
action
```
/
```
template
```
steps for deployments
Optionally create via MCP using
```
harness_create
```
with resource_type
```
pipeline
```

确认v1格式 - 用户必须明确需要v1语法。若不确定，默认使用v0（
```
/create-pipeline
```
）。
明确需求 - 流水线类型（CI、CD或两者兼具）、语言/框架、部署目标
参考规范文档 - 使用
```
references/v1-spec-schema.md
```
获取完整v1 schema、步骤类型、动作目录及示例

选择原生动作 - 优先使用原生动作和模板步骤，而非

run:

步骤。查阅

references/native-actions.md

获取完整映射。核心规则：

Docker构建/推送 → 使用

template: uses: buildAndPushToDocker

buildAndPushToECR

buildAndPushToGAR

（绝不要用

run: docker build && docker push

）

K8s部署 → 使用

action: uses: kubernetes-rolling-deploy

或

template: uses: k8sRollingDeployStep

（绝不要用

run: kubectl apply

）

Helm部署 → 使用

action: uses: helm-deploy

或

template: uses: helmDeployBasicStep

（绝不要用

run: helm upgrade --install

）

ECS部署 → 使用

template: uses: ecsBluegreenDeployStep

（绝不要用

run: aws ecs update-service

）

Terraform → 使用

template: uses: terraformStep

（绝不要用

run: terraform apply

）

安全扫描 → 使用原生STO模板（
```
gitleaksStep
```
、
```
banditStep
```
、
```
sbomOrchestrationStep
```
）

上传 → 使用

template: uses: uploadArtifactsToS3

uploadArtifactsToGCS

（绝不要用

run: aws s3 cp

）

审批 → 使用
```
approval: uses: harness
```
或
```
approval: uses: jira
```
（绝不要用轮询脚本）

工单 → 使用

action: uses: jira-create

snow-create

（绝不要用

run: curl

）

HTTP请求 → 使用

action: uses: http

或

template: uses: httpStep

（绝不要用

run: curl

）

仅当没有原生等效方案时，才使用
```
run:
```
步骤执行自定义构建/测试/检查命令

生成v1 YAML - 使用扁平化结构、
```
${{ }}
```
表达式、run步骤的
```
script
```
字段，以及部署用的
```
action
```
/
```
template
```
步骤
可选通过MCP创建 - 使用
```
harness_create
```
，resource_type设为
```
pipeline
```

v1 Key Differences from v0

v1与v0的核心差异

v0 Syntax	v1 Syntax
`<+variable>` expressions	`${{ variable }}` expressions
`type: CI` / `type: Deployment` stage types	Flat stages -- no `type` field
`command:` field in Run steps	`script:` field in `run:` steps
Native steps ( `K8sRollingDeploy` , `HelmDeploy` )	Action steps ( `action: uses: kubernetes-rolling-deploy` )
`failureStrategies:`	`on-failure:`
`HarnessApproval` step type	`approval: uses: harness` (stage-level or inline)
Deep nesting ( `spec: execution: steps:` )	Flat structure ( `steps:` )
`strategy: matrix:` under stage `spec`	`strategy: matrix:` directly on stage or step

v0语法	v1语法
`<+variable>` 表达式	`${{ variable }}` 表达式
`type: CI` / `type: Deployment` 阶段类型	扁平化阶段——无 `type` 字段
Run步骤中的 `command:` 字段	`run:` 步骤中的 `script:` 字段
原生步骤（ `K8sRollingDeploy` 、 `HelmDeploy` ）	动作步骤（ `action: uses: kubernetes-rolling-deploy` ）
`failureStrategies:`	`on-failure:`
`HarnessApproval` 步骤类型	`approval: uses: harness` （阶段级或内联）
深度嵌套（ `spec: execution: steps:` ）	扁平化结构（ `steps:` ）
阶段 `spec` 下的 `strategy: matrix:`	`strategy: matrix:` 直接定义在阶段或步骤上

Pipeline Structure

流水线结构

yaml

pipeline:
  name: My Pipeline
  repo:                          # optional: repository config
    connector: account.github
    name: myorg/my-repo
  clone:                         # optional: clone config
    depth: 1
  on:                            # optional: event triggers
  - push:
      branches: [main]
  env:                           # optional: global env vars
    NODE_ENV: production
  inputs:                        # optional: pipeline inputs
    branch:
      type: string
      default: main
  stages:
  - name: build
    steps:
    - run:
        script: go build

version:

kind:

, or

spec:

wrapper --

pipeline:

is the root key.

yaml

pipeline:
  name: My Pipeline
  repo:                          # 可选：仓库配置
    connector: account.github
    name: myorg/my-repo
  clone:                         # 可选：克隆配置
    depth: 1
  on:                            # 可选：事件触发器
  - push:
      branches: [main]
  env:                           # 可选：全局环境变量
    NODE_ENV: production
  inputs:                        # 可选：流水线输入
    branch:
      type: string
      default: main
  stages:
  - name: build
    steps:
    - run:
        script: go build

无需

version:

、

kind:

或

spec:

包裹——

pipeline:

为根键。

Stages

阶段

Stages have no

type

field. Their purpose is determined by their keys.

阶段无

type

字段，其用途由自身键值决定。

CI Stage

CI阶段

yaml

- name: build
  runtime: cloud
  platform:
    os: linux
    arch: arm
  cache:
    path: node_modules
    key: npm.${{ branch }}
  steps:
  - run:
      script: npm ci

yaml

- name: build
  runtime: cloud
  platform:
    os: linux
    arch: arm
  cache:
    path: node_modules
    key: npm.${{ branch }}
  steps:
  - run:
      script: npm ci

Deployment Stage

部署阶段

yaml

- name: deploy
  service: my-service
  environment: staging
  steps:
  - action:
      uses: kubernetes-rolling-deploy
      with:
        dry-run: false

yaml

- name: deploy
  service: my-service
  environment: staging
  steps:
  - action:
      uses: kubernetes-rolling-deploy
      with:
        dry-run: false

Approval (stage-level)

审批（阶段级）

yaml

- approval:
    uses: harness
    with:
      timeout: 30m
      message: "Approve deployment?"
      groups: [admins, ops]
      min-approvers: 1

yaml

- approval:
    uses: harness
    with:
      timeout: 30m
      message: "是否批准部署？"
      groups: [admins, ops]
      min-approvers: 1

Step Types

步骤类型

Run Step

Run步骤

Uses

script:

field (not

command:

run:

yaml

undefined

使用

script:

字段（而非

command:

或

run:

）。

yaml

undefined

long syntax

完整语法

run: script: npm test

run: script: npm test

short syntax

简化语法

run: npm test

run: npm test

with container

带容器

run: container: node:18 script: npm test

run: container: node:18 script: npm test

with shell and env

带Shell和环境变量

run: shell: bash script: | npm ci npm test env: NODE_ENV: test

run: shell: bash script: | npm ci npm test env: NODE_ENV: test

with output variables

带输出变量

id: build run: script: echo "TAG=v1" >> $HARNESS_OUTPUT output: [TAG]

undefined

id: build run: script: echo "TAG=v1" >> $HARNESS_OUTPUT output: [TAG]

undefined

Run Test Step

Run Test步骤

yaml

- run-test:
    container: maven
    script: mvn test
    report:
      type: junit
      path: target/surefire-reports/*.xml
    splitting:
      concurrency: 4

yaml

- run-test:
    container: maven
    script: mvn test
    report:
      type: junit
      path: target/surefire-reports/*.xml
    splitting:
      concurrency: 4

Action Step

Action步骤

Actions replace v0 native steps. See

references/v1-spec-schema.md

for the full action catalog.

yaml

undefined

动作替代了v0的原生步骤。查阅

references/v1-spec-schema.md

获取完整动作目录。

yaml

undefined

Kubernetes deploy

Kubernetes部署

action: uses: kubernetes-rolling-deploy with: dry-run: false

action: uses: kubernetes-rolling-deploy with: dry-run: false

Helm deploy

Helm部署

action: uses: helm-deploy with: timeout: 10m

action: uses: helm-deploy with: timeout: 10m

Terraform plan

Terraform计划

action: uses: terraform-plan with: command: apply aws-provider: account.aws_connector

action: uses: terraform-plan with: command: apply aws-provider: account.aws_connector

HTTP request

HTTP请求

action: uses: http with: method: GET endpoint: https://acme.com

undefined

action: uses: http with: method: GET endpoint: https://acme.com

undefined

Background Step

Background步骤

yaml

- background:
    container: redis
- run:
    script: npm test

yaml

- background:
    container: redis
- run:
    script: npm test

Template Step

Template步骤

yaml

- template:
    uses: account.docker@1.0.0
    with:
      push: true
      tags: latest

yaml

- template:
    uses: account.docker@1.0.0
    with:
      push: true
      tags: latest

Approval Step (inline)

审批步骤（内联）

yaml

- approval:
    uses: jira
    with:
      connector: account.jira
      project: PROJ

yaml

- approval:
    uses: jira
    with:
      connector: account.jira
      project: PROJ

Parallel and Group

并行与分组

yaml

undefined

yaml

undefined

parallel steps

并行步骤

parallel: steps:
- run: script: npm run lint
- run: script: npm test

parallel: steps:
- run: script: npm run lint
- run: script: npm test

parallel stages

并行阶段

parallel: stages:
- steps:
  - run: go test
- steps:
  - run: npm test

parallel: stages:
- steps:
  - run: go test
- steps:
  - run: npm test

step group

步骤分组

group: steps:
- run: script: go build
- run: script: go test

undefined

group: steps:
- run: script: go build
- run: script: go test

undefined

Strategy

策略

yaml

undefined

yaml

undefined

matrix (stage-level)

矩阵（阶段级）

strategy: matrix: node: [16, 18, 20] os: [linux, macos] max-parallel: 3 steps:
- run: container: node:${{ matrix.node }} script: npm test

strategy: matrix: node: [16, 18, 20] os: [linux, macos] max-parallel: 3 steps:
- run: container: node:${{ matrix.node }} script: npm test

matrix (step-level)

矩阵（步骤级）

strategy: matrix: go: [1.19, 1.20, 1.21] run: container: golang:${{ matrix.go }} script: go test

undefined

strategy: matrix: go: [1.19, 1.20, 1.21] run: container: golang:${{ matrix.go }} script: go test

undefined

Failure Strategy

失败策略

yaml

undefined

yaml

undefined

step-level

步骤级

run: script: go test on-failure: errors: all action: ignore # abort, ignore, retry, fail, success

run: script: go test on-failure: errors: all action: ignore # abort、ignore、retry、fail、success

retry with attempts

带重试次数的重试

run: script: go test on-failure: errors: [unknown] action: retry: attempts: 5 interval: 10s failure-action: fail

run: script: go test on-failure: errors: [unknown] action: retry: attempts: 5 interval: 10s failure-action: fail

stage-level

阶段级

steps:
- run: script: go test on-failure: errors: all action: abort

undefined

steps:
- run: script: go test on-failure: errors: all action: abort

undefined

Conditional Execution

条件执行

yaml

undefined

yaml

undefined

stage conditional

阶段条件

if: ${{ branch == "main" }} steps:
- run: script: deploy.sh

if: ${{ branch == "main" }} steps:
- run: script: deploy.sh

step conditional

步骤条件

if: ${{ branch == "main" }} run: script: deploy.sh

undefined

if: ${{ branch == "main" }} run: script: deploy.sh

undefined

Complete CI Example

完整CI示例

yaml

pipeline:
  repo:
    connector: account.github
    name: myorg/my-app
  clone:
    depth: 1
  on:
  - push:
      branches: [main]
  - pull_request:
      branches: [main]
  stages:
  - name: build-and-test
    runtime: cloud
    platform:
      os: linux
      arch: arm
    cache:
      path: node_modules
      key: npm.${{ branch }}
    steps:
    - run:
        script: npm ci
    - parallel:
        steps:
        - run:
            script: npm run lint
        - run-test:
            script: npm test
            report:
              type: junit
              path: junit.xml
    - action:
        uses: docker-build-push
        with:
          connector: dockerhub
          repo: myorg/my-app
          tags: [${{ pipeline.sequenceId }}, latest]

yaml

pipeline:
  repo:
    connector: account.github
    name: myorg/my-app
  clone:
    depth: 1
  on:
  - push:
      branches: [main]
  - pull_request:
      branches: [main]
  stages:
  - name: build-and-test
    runtime: cloud
    platform:
      os: linux
      arch: arm
    cache:
      path: node_modules
      key: npm.${{ branch }}
    steps:
    - run:
        script: npm ci
    - parallel:
        steps:
        - run:
            script: npm run lint
        - run-test:
            script: npm test
            report:
              type: junit
              path: junit.xml
    - action:
        uses: docker-build-push
        with:
          connector: dockerhub
          repo: myorg/my-app
          tags: [${{ pipeline.sequenceId }}, latest]

Complete CD Example

完整CD示例

yaml

pipeline:
  inputs:
    skip_dry_run:
      type: boolean
      default: false
  stages:
  - name: deploy-staging
    service: petstore
    environment: staging
    steps:
    - action:
        uses: manifest-download
    - action:
        uses: manifest-bake
    - action:
        uses: kubernetes-rolling-deploy
        with:
          dry-run: ${{ inputs.skip_dry_run }}
  - approval:
      uses: harness
      with:
        timeout: 1d
        message: "Approve production deployment?"
        groups: [prod-approvers]
        min-approvers: 1
  - name: deploy-prod
    service: petstore
    environment: prod
    steps:
    - action:
        uses: manifest-download
    - action:
        uses: manifest-bake
    - action:
        uses: kubernetes-rolling-deploy
        with:
          dry-run: false

yaml

pipeline:
  inputs:
    skip_dry_run:
      type: boolean
      default: false
  stages:
  - name: deploy-staging
    service: petstore
    environment: staging
    steps:
    - action:
        uses: manifest-download
    - action:
        uses: manifest-bake
    - action:
        uses: kubernetes-rolling-deploy
        with:
          dry-run: ${{ inputs.skip_dry_run }}
  - approval:
      uses: harness
      with:
        timeout: 1d
        message: "是否批准生产环境部署？"
        groups: [prod-approvers]
        min-approvers: 1
  - name: deploy-prod
    service: petstore
    environment: prod
    steps:
    - action:
        uses: manifest-download
    - action:
        uses: manifest-bake
    - action:
        uses: kubernetes-rolling-deploy
        with:
          dry-run: false

Creating via MCP

通过MCP创建

Verify the project exists — List projects with
```
harness_list
```
(resource_type:
```
project
```
, org_id) to confirm. If the project does not exist, create it first with
```
harness_create
```
(resource_type:
```
project
```
, body:
```
{ identifier, name }
```
) or ask the user.
Create the pipeline — Use
```
harness_create
```
with the v1 pipeline YAML serialized as a yamlPipeline
string in the body. Do not pass a nested JSON
```
pipeline
```
object; it causes serialization errors.

Call MCP tool: harness_create
Parameters:
  resource_type: "pipeline"
  org_id: "<organization>"
  project_id: "<project>"
  body: { yamlPipeline: "<full v1 pipeline YAML string, including 'pipeline:' root key>" }

验证项目存在 — 使用
```
harness_list
```
（resource_type:
```
project
```
, org_id）列出项目进行确认。若项目不存在，先使用
```
harness_create
```
（resource_type:
```
project
```
, body:
```
{ identifier, name }
```
）创建，或询问用户。
创建流水线 — 使用
```
harness_create
```
，将v1流水线YAML序列化为**
```
yamlPipeline
```
**字符串放入body中。请勿传递嵌套JSON格式的
```
pipeline
```
对象，否则会导致序列化错误。

调用MCP工具: harness_create
参数:
  resource_type: "pipeline"
  org_id: "<organization>"
  project_id: "<project>"
  body: { yamlPipeline: "<完整v1流水线YAML字符串，包含'pipeline:'根键>" }

Examples

示例

Create a v1 CI pipeline

创建v1 CI流水线

/create-pipeline-v1
Create a v1 CI pipeline for a Node.js app with caching, parallel lint and test, and Docker push

/create-pipeline-v1
为Node.js应用创建带缓存、并行检查和测试、Docker推送的v1 CI流水线

Create a v1 deployment pipeline

创建v1部署流水线

/create-pipeline-v1
Create a v1 Kubernetes deployment pipeline with staging approval and production stages

/create-pipeline-v1
创建带预发布环境审批和生产环境阶段的v1 Kubernetes部署流水线

Create a v1 matrix build

创建v1矩阵构建

/create-pipeline-v1
Create a v1 pipeline that tests across Go 1.19, 1.20, and 1.21 using matrix strategy

/create-pipeline-v1
创建使用matrix策略在Go 1.19、1.20和1.21版本进行测试的v1流水线

Performance Notes

性能注意事项

Always check
```
references/native-actions.md
```
before using a
```
run:
```
step. Native actions provide better error handling, rollback support, and UI integration.
Always consult
```
references/v1-spec-schema.md
```
for the complete v1 spec before generating YAML.
Use
```
script:
```
field in run steps, never
```
command:
```
or
```
run:
```
as the field name.
Use
```
action: uses:
```
or
```
template: uses:
```
for deployments, never v0 native step types like
```
K8sRollingDeploy
```
.
Do not mix v0 and v1 syntax. No
```
<+...>
```
expressions, no
```
type:
```
on stages, no
```
spec:
```
wrapper.
Validate all expressions use
```
${{ }}
```
syntax before presenting.

使用
```
run:
```
步骤前务必查阅
```
references/native-actions.md
```
。原生动作提供更优的错误处理、回滚支持和UI集成。
生成YAML前务必查阅
```
references/v1-spec-schema.md
```
获取完整v1规范。
run步骤中使用
```
script:
```
字段，绝不要用
```
command:
```
或
```
run:
```
作为字段名。
部署时使用
```
action: uses:
```
或
```
template: uses:
```
，绝不要用v0原生步骤类型如
```
K8sRollingDeploy
```
。
不要混合v0和v1语法。禁止使用
```
<+...>
```
表达式、阶段的
```
type:
```
字段、
```
spec:
```
包裹层。
展示前验证所有表达式使用
```
${{ }}
```
语法。

Troubleshooting

故障排查

Common v1 Syntax Errors

常见v1语法错误

Using
```
<+...>
```
instead of
```
${{ ... }}
```
expressions
Adding
```
type:
```
field on stages (v1 stages have no type)
Using
```
command:
```
or
```
run:
```
as the field name instead of
```
script:
```
Wrapping pipeline in
```
version:
```
,
```
kind:
```
,
```
spec:
```
(v1 uses bare
```
pipeline:
```
)

Using v0 step types (

K8sRollingDeploy

) instead of actions (

action: uses: kubernetes-rolling-deploy

)

Using
```
failureStrategies:
```
instead of
```
on-failure:
```

使用
```
<+...>
```
而非
```
${{ ... }}
```
表达式
为阶段添加
```
type:
```
字段（v1阶段无类型）
使用
```
command:
```
或
```
run:
```
作为字段名而非
```
script:
```
用
```
version:
```
、
```
kind:
```
、
```
spec:
```
包裹流水线（v1直接使用
```
pipeline:
```
）

使用v0步骤类型（

K8sRollingDeploy

）而非动作（

action: uses: kubernetes-rolling-deploy

）

使用
```
failureStrategies:
```
而非
```
on-failure:
```

MCP Errors

MCP错误

Project not found — Verify the project exists with
```
harness_list
```
(resource_type:
```
project
```
, org_id). Create it first or confirm org_id/project_id are correct.
Missing required fields for pipeline: pipeline — Pass the body as
```
{ yamlPipeline: "<full v1 pipeline YAML string>" }
```
instead of a nested JSON
```
pipeline
```
object.
```
DUPLICATE_IDENTIFIER
```
— Pipeline exists; use
```
harness_update
```
```
INVALID_REQUEST
```
— Check YAML structure matches v1 schema

项目未找到 — 使用
```
harness_list
```
（resource_type:
```
project
```
, org_id）验证项目是否存在。先创建项目或确认org_id/project_id正确。
Missing required fields for pipeline: pipeline — 将body传递为
```
{ yamlPipeline: "<完整v1流水线YAML字符串>" }
```
，而非嵌套JSON格式的
```
pipeline
```
对象。
```
DUPLICATE_IDENTIFIER
```
— 流水线已存在；使用
```
harness_update
```
```
INVALID_REQUEST
```
— 检查YAML结构是否匹配v1 schema