DevOps Pipeline Management

What it does

When your agent uses it

• Searching for a workspace or pipeline on the platform
• Creating a pipeline from a template
• Running or cancelling a pipeline and checking its status or logs
• Adding, changing or removing task nodes in an existing pipeline

Example prompts

• “List the workspaces in our organization and show the pipelines in the payments one.”
• “Create a pipeline from the Java build template and preview the configuration before saving it.”
• “Run the release pipeline in non-interactive mode and report its status when it finishes.”

Requirements

• Python 3.8 or later with the Requests library
• Access to the platform's OpenAPI endpoints

Workflow steps

7 steps, taken from the step headings in SKILL.md.

1. 1系统要求
2. 2依赖安装
3. 3获取 API 凭证
4. 4验证配置
5. 5查询工作空间
6. 6查询流水线列表
7. 7执行流水线

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • one-dev.iflytek.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

DevOps Pipeline Management loads about 4.2k tokens when it runs, and up to ~129k if it reads all its reference files. Until then it costs about 185 tokens; SKILL.md has 685 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~185

When it runs · the whole SKILL.md, loaded when a task matches

~4.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~129k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteRuns commands with sudoSKILL.md:216

  sudo ln -s $(pwd)/scripts/main.py /usr/local/bin/devops-pipeline

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 685 words, ~4,227 tokens.

name

devops-pipeline-management

description

Expert for DevOps pipeline management, handling the complete lifecycle of pipelines on the quality and efficiency platform. Core capabilities: 1) Workspace management - Query workspace lists with filtering 2) Pipeline management - Create, query, update, and delete pipelines 3) Execution management - Execute and cancel pipelines, query execution records and details 4) Template management - Query pipeline templates and create pipelines from templates Trigger scenarios: - Users need to search for workspaces or pipelines - Users need to execute or run pipelines - Users need to check pipeline execution status or logs - Users need to create, update, or delete pipelines - Users need to query pipeline templates

pip install requests

pip install -r requirements.txt

# 域账号（必填）
export DEVOPS_DOMAIN_ACCOUNT="your_domain_account"

# BFF 服务地址（必填）
export DEVOPS_BFF_URL="https://one-dev.iflytek.com/devops"

# 交互模式开关（默认：true）
# true: 执行流水线时询问是否交互式选择分支/标签/版本
# false: 自动使用最近执行记录填充，不询问
export INTERACTIVE_MODE="true"

# DevOps Pipeline Skill 配置
export DEVOPS_DOMAIN_ACCOUNT="your_domain_account"
export DEVOPS_BFF_URL="https://one-dev.iflytek.com/devops"
export INTERACTIVE_MODE="true"  # 启用交互式选择功能

source ~/.zshrc  # 或 source ~/.bashrc

cd devops-skills/pipeline-management
python -m scripts/main --help

# 添加软链接（可选：使用 devops-pipeline 作为命令名）
sudo ln -s $(pwd)/scripts/main.py /usr/local/bin/devops-pipeline

# 使用
devops-pipeline --help      # 需要创建符号链接

python -m scripts/main

python -m scripts/main workspaces --name devops

python -m scripts/main pipelines <space_id>

python -m scripts/main run <pipeline_id>

1. workspaces          → 获取工作空间列表，找到目标空间ID
2. pipelines <spaceId> → 获取空间下的流水线列表，找到目标流水线ID
3. run <pipelineId>    → 执行流水线
4. list <pipelineId>   → 查看执行记录
5. run-detail <id>     → 查看执行详情

1. 解析用户输入 → 从自然语言提取 spaceId、流水线名称、技术栈等信息
2. 补充必填信息 → 交互式补充缺失的 spaceId、流水线名称等
3. 查询模板并选择 → 查询模板列表，交互式选择适合的模板
4. 模板数据转换 → 将模板数据转换为流水线数据，生成新UUID
5. 配置代码源 → 交互式配置代码仓库、分支等源代码信息
6. 配置任务节点 → 交互式配置任务参数、执行路径等
7. 配置预览 → 展示完整配置供用户确认
8. 保存流水线 → 调用 `save` 命令保存流水线配置
9. 执行流水线 → 调用 `run` 命令执行新创建的流水线

1. list <pipelineId>       → 查看执行记录列表
2. run-detail <logId>      → 查看具体执行详情
3. cancel <logId>          → 如需取消正在执行的流水线

# 查询所有工作空间
python -m scripts/main workspaces

# 按名称搜索
python -m scripts/main workspaces --name devops

# 按组织筛选
python -m scripts/main workspaces --division "研发中心"

# 按产品线筛选
python -m scripts/main workspaces --team "DevOps平台"

# 分页查询
python -m scripts/main workspaces --page 2 --size 20

# 查询空间 133 的流水线列表
python -m scripts/main pipelines 133

# 按名称搜索
python -m scripts/main pipelines 133 --name 构建

# 分页查询
python -m scripts/main pipelines 133 --page-num 2 --page-size 20

# 查询空间 133 的模板列表
python -m scripts/main templates 133

# 按名称搜索
python -m scripts/main templates 133 --name Java

# 按类型筛选
python -m scripts/main templates 133 --type 1

# 按编程语言筛选
python -m scripts/main templates 133 --language java

# 分页查询
python -m scripts/main templates 133 --page 1 --size 20

# 1. 查询工作空间获取 space_id（可选，用于确认空间）
python -m scripts/main workspaces --name devops

# 2. 查询可用模板（可选，用于了解可用模板）
python -m scripts/main templates 133 --name "Java微服务"

# 3. 创建流水线配置（遵循9步骤规范）
#    步骤1-7：交互式收集配置信息
#    步骤8：使用 save 命令保存流水线配置
python -m scripts/main save --config '{"pipelineId": "新生成的UUID", "name": "我的Java流水线", "spaceId": 133, ...}'

# 4. 执行流水线（步骤9）
python -m scripts/main run <新创建的pipeline_id>

# 仅创建配置，不执行（步骤1-8）
# 遵循9步骤规范的前8步，生成流水线配置后使用 save 命令保存
python -m scripts/main save --file pipeline-config.json

# 更新已创建的流水线配置（遵循6步骤规范）
# 遵循 [pipeline-update.md](references/pipeline-update.md) 的6步骤规范
python -m scripts/main save --config '{"pipelineId": "现有pipelineId", "name": "更新后的名称", ...}'

# 执行已创建的流水线
python -m scripts/main run <pipeline_id>

python -m scripts/main detail 4059831ef9ee41d3ad7d7c4c4be567b1

# 基本执行（使用默认配置）
python -m scripts/main run 4059831ef9ee41d3ad7d7c4c4be567b1

# 指定分支执行
python -m scripts/main run 4059831ef9ee41d3ad7d7c4c4be567b1 --branch feature/new-feature

# 指定执行的任务节点
python -m scripts/main run 4059831ef9ee41d3ad7d7c4c4be567b1 --tasks task-1,task-2

# 自动填充上次配置
python -m scripts/main run 4059831ef9ee41d3ad7d7c4c4be567b1 --auto-fill

# 非交互模式执行
python -m scripts/main run 4059831ef9ee41d3ad7d7c4c4be567b1 --non-interactive

# 查询执行记录列表
python -m scripts/main list 4059831ef9ee41d3ad7d7c4c4be567b1

# 分页查询
python -m scripts/main list 4059831ef9ee41d3ad7d7c4c4be567b1 --page-num 1 --page-size 20

# 按状态搜索
python -m scripts/main list 4059831ef9ee41d3ad7d7c4c4be567b1 --type status --keyword success

python -m scripts/main run-detail 22579

python -m scripts/main cancel 22579

# 创建流水线（遵循9步骤规范，使用 save 命令）
# 生成新的 pipelineId
python -m scripts/main save --config '{"pipelineId": "新生成的UUID", "name": "我的流水线", "spaceId": 133, "stages": [...], "sources": [...]}'

# 如果需要指定任务数据
python -m scripts/main save --config '{"pipelineId": "新生成的UUID", "name": "我的流水线", "spaceId": 133}' --task-data '[{"id": "task-001", "data": {...}}]'

# 从JSON文件创建
python -m scripts/main save --file pipeline-config.json

# 更新流水线（遵循6步骤规范，使用 save 命令）
# 保留原 pipelineId，更新需要修改的字段
python -m scripts/main save --config '{"pipelineId": "现有pipelineId", "name": "新名称", "spaceId": 133, ...}'

# 从JSON文件更新
python -m scripts/main save --file updated-pipeline-config.json

# 同时更新任务数据
python -m scripts/main save --config '{"pipelineId": "现有pipelineId", "name": "新名称", "spaceId": 133}' --task-data '[{"id": "task-001", "data": {...}}]'

python -m scripts/main delete 4059831ef9ee41d3ad7d7c4c4be567b1

============================================================
[Request] POST https://one-dev.iflytek.com/devops/api/ai-bff/rest/openapi/pipeline/runByManual
------------------------------------------------------------
Headers:
  X-User-Account: rfdai
------------------------------------------------------------
Body: {...}
============================================================

============================================================
[Response] Status: 200
------------------------------------------------------------
Response Body: {...}
============================================================

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 104 other files (scripts, references, assets) in skills/devops-pipeline-management of LeoYeAI/openclaw-master-skills.

• SKILL.md
• README.md
• _meta.json
• assets/README.md
• references/excute-pipeline-logic.md
• references/pipeline-cancel.md
• references/pipeline-create.md
• references/pipeline-delete.md
• references/pipeline-detail.md
• references/pipeline-list.md
• references/pipeline-page.md
• references/pipeline-run-detail.md
• references/pipeline-run.md
• references/pipeline-task-add.md
• references/pipeline-task-delete.md
• references/pipeline-task-update.md
• references/pipeline-template.md
• references/pipeline-update.md
• references/pipeline
• … and 86 more

Open the folder on GitHubat commit e5199b5