See which failing Ghost Inspector tests have no Jira owner

**Objective:** Report the health of Ghost Inspector suite {suite-name} and set it against the open bug backlog in Jira project {jira-project-key}, over the last {lookback-days} days (default 14), so the worst tests with no owner are visible. This prompt reports only. It creates and changes nothing.

**Step 1: The suite**

Call `ghost-inspector-get-suite` on the ghost-inspector server with `name.contains` set to {suite-name}. Keep its id, test count, organization, browser, region and frequency. If more than one suite matches, list them and stop.

**Step 2: Suite-level history**

Call `ghost-inspector-get-suite-result` with `suite-id` set to the suite's id and `date-created.from` set to the start of the window, `max-records` 100. From the passing, failing and unknown counts on each row, work out the suite pass rate across the window and whether it is improving or worsening between the first and second half of it.

**Step 3: Test-level history**

Call `ghost-inspector-get-test-result` with `suite-id` set to the suite's id and the same `date-created.from`, `max-records` 300.

For each distinct test name, count runs and failures and compute a failure rate. Rank the tests by failure rate, breaking ties by number of runs.

**Step 4: Match to the backlog**

For each test with at least one failure, call `jira-get-issue` on the jira server with `project-key` set to {jira-project-key} and `summary.contains` set to the test name, `max-records` 20. Record the key, status and assignee of any issue that is not Done, Closed or Resolved.

**Step 5: Report**

Lead with one line: the suite name, its pass rate across the window, the direction of travel, and how many of its failing tests have no open ticket.

Then a table, worst first: test name, runs, failures, failure rate, browsers it fails on, Jira issue key or the word none, Jira status, assignee or unassigned.

Then a short ranked list of what to act on first. Put an untracked test failing most of the time above a tracked one that fails occasionally, and say why each entry is where it is.

**Rules & Guidelines:**

* `ghost-inspector-get-suite`, `ghost-inspector-get-suite-result` and `ghost-inspector-get-test-result` are on the ghost-inspector server. `jira-get-issue` and `jira-get-project` are on the jira server. All three servers must be connected.
* The linking convention used by every prompt on this server: a Jira issue raised from a Ghost Inspector failure has a summary beginning `Ghost Inspector failure: ` followed by the test name, and its first comment contains the line `Ghost Inspector result id: ` followed by the result id. Matching in both directions depends on this, so do not vary the wording.
* Do NOT call any write tool. Specifically do not call `jira-add-issue`, `jira-add-issue-comment`, `jira-update-issue`, `jira-assign-issue`, `ghost-inspector-execute-suite`, `ghost-inspector-execute-test`, `ghost-inspector-update-suite` or `ghost-inspector-add-suite-result-comment`.
* Report a failure rate only where there were at least three runs in the window, and mark thinner tests as insufficient data rather than showing a rate from one run.

**Validation:**

* If the suite has no results in the window, report that it has not run and check its frequency setting to say whether it is scheduled at all.
* If `jira-get-issue` returns nothing for every test, confirm the project key with `jira-get-project` before reporting the whole suite as untracked.
* If a test's failures all fall on one browser or region, say so on its row. It changes what the fix is.