agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/email/customer-reply-tone-match/SKILL.md

customer-reply-tone-match

Skill0 starsChanged 4 months agoMITView on GitHub

Read the tone of the inbound message — clipped, warm, frustrated, formal — and answer in a register that fits instead of one flat default. Replying to any customer or prospect message. Especially when they're upset or unusually casual — a mismatch reads as tone-deaf.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read how they wrote before you decide how to answer.

    line 16
  2. Distinctive:

    Read the inbound for tone, not just content: word count, punctuation, whether they're warm or clipped, calm or hot.

    line 20
  3. Distinctive:

    If they're frustrated, lead by naming the problem and owning it — not with a defense and not with forced cheer.

    line 21
  4. Distinctive:

    If they wrote two casual lines, don't answer with five formal paragraphs.

    line 22
  5. Distinctive:

    Never out-escalate. If they're annoyed, you're calm and direct.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Match the Customer's Tone

Read how they wrote before you decide how to answer. A frustrated customer needs acknowledgment first; a one-line text gets a one-line reply. Matching the register makes the answer land.

The technique

  • Read the inbound for tone, not just content: word count, punctuation, whether they're warm or clipped, calm or hot.
  • If they're frustrated, lead by naming the problem and owning it — not with a defense and not with forced cheer.
  • If they wrote two casual lines, don't answer with five formal paragraphs. Mirror the length.
  • Stay in the owner's voice while you match their register — match energy, not their exact words or grammar.
  • Never out-escalate. If they're annoyed, you're calm and direct; you don't match anger with anger.

Do this, not that

Do: They wrote: "Still no invoice. This is the third time I've asked." You answer: "That's on me — sending it in the next five minutes, and I'll confirm once it's in your inbox. Sorry you had to ask three times."

Don't: Answer that same frustrated message with "Thank you so much for reaching out! We truly value your business and appreciate your patience. We'll look into this for you!" — chipper at someone who's mad reads as not listening.

Why this works

Tone is most of the message. The same words land completely differently depending on whether they meet the customer where they are. A frustrated person who gets a cheerful auto-reply feels unheard and gets angrier; one who gets a calm, owning answer feels handled. Reading the register first is how a reply defuses instead of inflames.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.