Build a Support Macro Library From Old Tickets

Your best support answers already exist. They are scattered across a year of tickets, written once, and never reused.

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 leads and small teams with no knowledge base.

How it works

The skill file does five things, in this order.

1. Export tickets to CSV. Subject, body, resolution, and time-to-close if you have it.

2. Cluster by real intent. Not by tag. Tags lie. Cluster by what the customer actually wanted.

3. Pick the best answer per cluster. Judged on resolution speed and whether the ticket reopened.

4. Rewrite as a reusable macro. With variables for name, order, and date.

5. Rank clusters by volume. The top five usually cover more than half your queue.

What comes back

A ranked macro library with variables, plus the product fixes that would delete each cluster.

The mistake to avoid

Ask for the product fix alongside every macro. A macro answers the question forever; a fix means the question stops being asked.

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

Analyse this ticket export and build a support macro library.

1. Cluster tickets by customer intent, ignoring existing tags.
2. For the top 10 clusters report: volume, share of total, median time to close,
   reopen rate.
3. For each cluster, select the single best historical reply and rewrite it as a
   macro with {customer_name}, {order_ref}, {date} variables. Keep our tone.
4. For each cluster, name the one product or process change that would make the
   cluster disappear, and estimate the tickets per month it would remove.

Output the macros as ready-to-paste blocks.
<tickets>{CSV}</tickets>