dx-ticket-analyze

Defaults

Read shared/provider-config.md for provider detection and tool mapping.

Read .ai/config.yaml:

• tracker.provider (or scm.provider for backward compat) — ado (default) or jira

If provider = ado:

• Organization: scm.org
• Project: scm.project

If provider = jira:

• Jira URL: jira.url
• Project Key: jira.project-key

You receive an ADO ticket URL/ID or Jira issue key, extract all relevant info, and produce a structured developer reference showing every file and asset they need.

1. Parse Input

Accept any of these formats:

• Full ADO URL: https://{org}.visualstudio.com/{project}/_workitems/edit/{id}
• Full ADO URL: https://dev.azure.com/{org}/{project}/_workitems/edit/{id}
• Full Jira URL: https://{host}/browse/{KEY-123}
• Jira issue key: KEY-123 (matches /^[A-Z]+-\d+$/)
• Short numeric: {id}

Extract:

• Work Item ID — numeric ID from ADO URL
• Issue Key — from Jira URL or key format
• Project — from URL path if present. Default: read from .ai/config.yaml scm.project (ADO) or jira.project-key (Jira)

If the argument is purely numeric, check tracker.provider to determine if it's an ADO ID or a Jira issue number (prepend project key).

If no argument provided, ask the user for the ADO URL, Jira URL, or ticket ID.

2. Fetch Ticket

Use ADO MCP to get the work item:

mcp__ado__wit_work_item
  action: "get"
  project: <extracted project>
  id: <work item ID>
  expand: "Relations"

If provider = jira

mcp__atlassian__jira_get_issue
  issue_key: "<issue key>"

Map Jira fields (see shared/provider-config.md Field Mapping):

• Title — fields.summary
• State — fields.status.name
• Assigned To — fields.assignee.displayName
• Iteration Path — fields.sprint.name
• Tags — fields.labels[]
• Parent — fields.parent.key and fields.parent.fields.summary
• Children — fetch via mcp__atlassian__jira_search with JQL parent = <issue_key>
• Issue links — from the response's fields.issuelinks[] (replaces ADO relations)