Train Your Support Team to Write Consistent Macros
Get every agent writing on-brand macros without a style guide spiral
You have five agents generating macros and each one sounds like a different company. Customers notice the tonal whiplash between formal Ahmed and casual Sara.
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 distributing AI macro creation across a team
How it works
The skill file does five things, in this order.
1. Document three reference macros as gold standard. Pick your best existing macros for refund, delay, and bug scenarios, then label what makes each one work.
2. Build a team prompt that references those examples. Give Claude your gold macros and have it extract tone rules, then embed those rules into a reusable prompt all agents share.
3. Create a two-macro test for each agent. Have every team member generate one easy and one difficult macro using the shared prompt, then compare outputs in a review session.
4. Log who wrote what in your macro metadata. Tag each macro with author name and date so you can trace quality issues back to specific training gaps.
5. Run monthly audits on tone drift. Sample ten macros created that month and ask Claude if they match your gold standard, then share the drift report with the team.
What comes back
A shared prompt and review rhythm that keeps ten agents sounding like one voice
The mistake to avoid
Version your team prompt in a shared doc with a changelog. When tone standards shift, agents know exactly which version to use and why it changed.
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
You are a tone consistency auditor for a support team.
Our three gold standard macros are:
1. {macro_example_1}
2. {macro_example_2}
3. {macro_example_3}
Analyze these macros and extract:
- Sentence length patterns
- Greeting and closing formulas
- Use of contractions or formal language
- How we acknowledge customer frustration
- When we use passive vs active voice
- Emoji or punctuation norms
Then write a clear style ruleset (maximum 8 rules) that any agent can follow when drafting new macros.
After that, take this new macro draft:
{new_macro_draft}
Score it against your ruleset (0-10 for each rule).
Finally, rewrite the draft to match our gold standard tone perfectly while keeping the same factual content.
Format:
## Extracted Style Rules
## Scores
## Rewritten Macro