Pull Ticket Context (ACLI)
Fetches a ticket and its full picture — subtasks, comments, linked context — and packages it as a structured block for agent or human consumption.
Procedure
- •Fetch the target ticket (full fields including description):
code
acli jira workitem view KEY-123 --fields "key,summary,status,assignee,priority,issuetype,description" --json
- •Fetch subtasks:
code
acli jira workitem search --jql "parent = KEY-123" --fields "key,summary,status" --csv
- •Fetch recent comments:
code
acli jira workitem comment-list --key "KEY-123"
- •Package as structured context:
code
## KEY-123: "Title" Status: In Progress | Priority: High | Assignee: user@email.com Type: Story | Sprint: Sprint 42 ### Description [full description text] ### Subtasks - KEY-124: "Subtask A" [Done] - KEY-125: "Subtask B" [In Progress] ### Recent Comments (last 5) - Alice (2d ago): "Blocked on API access" - Bob (1d ago): "Unblocked, credentials shared"
Always use this output format. Downstream skills depend on its structure.
If the ticket has no subtasks or comments, omit those sections rather than showing empty headings.
Error Handling
If ACLI returns exit code != 0:
- •"authentication failed" → Tell user:
acli jira auth login --web --site <site>.atlassian.net - •"command not found: acli" → Tell user:
brew tap atlassian/homebrew-acli && brew install acli - •"trace id:" prefix → Unexpected server error, report trace ID
- •Other → Report raw error message