Agent Skills › pony-maggie/code_minions › create-jira-tickets

create-jira-tickets

GitHub

通过Jira MCP创建Epic和Story，关联任务数据并返回票据引用。

src/code_minions/builtin/skills/create-jira-tickets/SKILL.md pony-maggie/code_minions

Trigger Scenarios

需要批量创建Jira Epic和Story 将规划任务同步至Jira项目管理

Install

npx skills add pony-maggie/code_minions --skill create-jira-tickets -g -y

More Options

Non-standard path

npx skills add https://github.com/pony-maggie/code_minions/tree/main/src/code_minions/builtin/skills/create-jira-tickets -g -y

Use without installing

npx skills use pony-maggie/code_minions@create-jira-tickets

指定 Agent (Claude Code)

npx skills add pony-maggie/code_minions --skill create-jira-tickets -a claude-code -g -y

安装 repo 全部 skill

npx skills add pony-maggie/code_minions --all -g -y

预览 repo 内 skill

npx skills add pony-maggie/code_minions --list

SKILL.md

Frontmatter

{
    "llm": {
        "temperature": 0.1,
        "max_iterations": 30
    },
    "name": "create-jira-tickets",
    "inputs": {
        "tasks": {
            "type": "array",
            "required": true
        },
        "epic_title": {
            "type": "string",
            "required": true
        },
        "project_key": {
            "type": "string",
            "required": true
        }
    },
    "outputs": {
        "epic": {
            "type": "object"
        },
        "errors": {
            "type": "array"
        },
        "tickets": {
            "type": "array"
        }
    },
    "description": "Create Jira Epic + Stories for a list of planned tasks.",
    "allowed-tools": [],
    "required-mcps": [
        "jira"
    ]
}

create-jira-tickets

Create a Jira Epic + Stories for each task, return the created ticket references.

Inputs

tasks (object[], required): output of plan-tasks.
project_key (string, required): Jira project key (e.g. "ABC").
epic_title (string, required): title for the umbrella epic.

Instructions

Use the jira MCP server's tools. Typical calls: create_issue with issuetype.
Create ONE Epic first, capture its key, then create all stories with customfield_* = Epic link or parent reference (whichever the MCP supports).
If a Jira API call returns an error, record it in errors rather than retrying blindly.
Preserve the original planned task data in every returned ticket object. The downstream implementer consumes tickets directly, so each ticket must keep the task id, title, description, acceptance_criteria, depends_on, and any delivery_profile exactly as received.
Add Jira metadata to the preserved task object instead of replacing the task with a thin reference. Use task_id for the original task id and include ticket_key plus url when available.