Score Your Support Macros by Actual Customer Satisfaction

You built a macro library months ago but have no idea which templates make customers happy and which ones tank your CSAT scores. You keep using the same replies because they save time, even when they might be causing escalations.

That is the gap this drop closes. It is a operations skill built for Claude, and it takes about ten minutes to set up the first time. After that it runs in under a minute.

Who should use it

Support managers who already use macros and want to know which ones actually work

How it works

The skill file does five things, in this order.

1. Export tickets with macro tags and satisfaction scores. Pull the last 90 days of closed tickets showing which macro was used and the customer rating that followed.

2. Ask Claude to calculate average CSAT by macro. Feed the spreadsheet to Claude and ask it to rank each macro by mean satisfaction score and flag any below your target threshold.

3. Request a breakdown of low performers by issue type. Have Claude group underperforming macros by ticket category to see if certain templates fail only in specific contexts.

4. Generate rewrite suggestions for the bottom quartile. Ask Claude to draft alternative versions of your three worst macros based on patterns it sees in higher rated responses.

5. Set a review cadence in your calendar. Schedule this analysis monthly so you catch drifting macro performance before it becomes a pattern.

What comes back

A ranked list of your macros by customer satisfaction impact, plus draft replacements for the ones hurting your scores

The mistake to avoid

Filter out tickets where the customer never responded to a satisfaction survey. Missing scores skew the average and make good macros look worse than they are.

Running it

Save this as SKILL.md inside a folder named after the skill, then drop the folder into your Claude Code skills directory or upload it to a Claude Project. Claude reads the frontmatter to decide when the skill applies, so keep the description line intact. For a one-off run, paste the prompt block directly.

Where this fits

On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.

In the file

I have a spreadsheet of customer support tickets with the following columns:
- Ticket ID
- Macro name used (the templated reply)
- Customer satisfaction score (1-5 scale, where 5 is best)
- Ticket category
- Resolution date

Please do the following:

1. Calculate the average satisfaction score for each macro name
2. Rank all macros from highest to lowest average score
3. Flag any macro with an average score below {target_score}
4. For macros below the threshold, group them by ticket category and show how many times each was used in each category
5. Identify the {number} worst performing macros overall
6. For those worst performers, analyze the text of the macro (I will paste them) and suggest specific changes that might improve customer perception, based on patterns you notice in our higher rated macros

Here is the data:
{paste_spreadsheet}

Here are the actual macro texts for the bottom performers:
{paste_macro_texts}