Support ticket trend analysis and fixes

Analyze the batch of support tickets below for {{product}} and tell me what to fix.

Ticket data (one per line or pasted export):
{{tickets}}

Period and volume: {{period}}
Team goal: {{goal}}

Do this:
1. Group tickets into 5-8 themes. For each theme: name, approximate count and percentage, a representative customer quote (names removed), and the likely root cause.
2. Classify each theme's best fix: product change, documentation or help article, in-app copy, macro or training, or no action. Explain the choice briefly.
3. Rank the top 5 actions by expected ticket reduction against effort. Show your reasoning as High/Medium/Low for each.
4. Highlight anything unusual: sudden spikes, high-emotion tickets, churn risk, security or legal issues.
5. State the limits of this analysis: sample size, ambiguous tickets, anything you couldn't classify.

Count honestly; if the data is too small to draw conclusions, say so. Do not invent numbers, and show how you got each count.

Output as a short report with a table for theme counts and a numbered action list.