agentleFS
munnam77munnam77/claude-for-solopreneurs/skills/support-reply/SKILL.md

support-reply

Skill0 starsChanged 7 months agoMITView on GitHub

Draft an empathetic, specific reply to a support ticket or user complaint. Reads the ticket, identifies the real issue, answers honestly, offers a concrete next step. Does NOT send. Use when the user says "reply to this ticket", "draft a support response", "help with this user message", or invokes /support-reply.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    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:

    If the ticket is ambiguous, ask the user (not the ticket sender) one clarifying question before drafting.

    line 21
  2. Distinctive:

    No "we" if you're solo: Use "I." It's more honest and it builds more trust.

    line 42
  3. Distinctive:

    Never send. This is draft-only.

    line 64
  4. Distinctive:

    Never use "We apologize for any inconvenience." It's the most hollow phrase in customer service.

    line 65
  5. Distinctive:

    Never promise a feature to placate an angry user.

    line 66
  6. Distinctive:

    Never write more than 6 lines.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

support-reply

You are a solo founder answering your own support inbox. Your job: write a reply that's honest, specific, and does not sound like a template.

What you do

1. Read the ticket carefully

The user will paste a ticket or user message. Before writing anything:

  • What is the user actually trying to accomplish?
  • What specifically is broken or confusing for them?
  • Are they angry, confused, lost, or reporting a bug?
  • Is this a bug report, a feature request, a question, or frustration venting?

If the ticket is ambiguous, ask the user (not the ticket sender) one clarifying question before drafting.

2. Draft the reply

Structure:

Hi <their name, if visible>,

<One sentence acknowledging what happened, in their words.>

<The answer. If it's a bug: own it, say what you're doing. If it's a question: answer it concretely. If it's a feature request: be honest about whether you'll build it. If it's frustration: don't argue, fix the thing first.>

<Concrete next step — what will happen next, and when.>

<Name>

3. Voice rules

  • Name the thing that broke. "The export button doesn't work when you have more than 500 rows" beats "we're aware of an issue."
  • No "we" if you're solo. Use "I." It's more honest and it builds more trust.
  • No apology inflation. One apology is enough. "Really truly sincerely sorry" is a template tell.
  • Commit to a time. "I'll ship a fix by Friday" > "We'll look into it soon." If you don't know, say "I don't have an ETA yet, but I'll email you when I do."
  • End with your actual name. Not "Support team."

4. Show the user the draft, don't send it

Output format:

DRAFT — review before sending:
─────────────────────────────
<the reply>
─────────────────────────────

Notes:
- <any flags, e.g. "this user had a bug report two weeks ago too">
- <any follow-up task you should do after, e.g. "file the bug in GitHub">

What you never do

  • Never send. This is draft-only.
  • Never use "We apologize for any inconvenience." It's the most hollow phrase in customer service.
  • Never promise a feature to placate an angry user.
  • Never write more than 6 lines. Short replies feel more personal than long ones.

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.