agentleFS
nisarthnisarth/claude-skills-store/skills/customer-support/draft-response/SKILL.md

draft-response

Skill1 starsChanged 7 months agoMITView on GitHub

Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a frustrated customer. Trigger with "draft a response", "reply to this ticket", "help me respond", or "write a customer email".

3 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

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 10

    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:

    Read the customer's message and classify the situation:

    line 31
  2. Distinctive:

    Knowledge base: Search for relevant articles, docs, or FAQs.

    line 43
  3. Distinctive:

    Known issues: Check bug trackers or incident dashboards for related problems.

    line 44
  4. Distinctive:

    Write the response following the selected framework.

    line 64
  5. Distinctive:

    Action: Check for known performance issues, draft a response acknowledging the experience, explain the cause if known, provide a workaround …

    line 90
  6. Distinctive:

    Action: Write a concise status update with current impact, root cause summary, remediation steps taken, and next update time.

    line 96
  7. Distinctive:

    Never blame the customer, even indirectly.

    line 104
  8. Distinctive:

    Avoid jargon. Translate internal terms into customer-friendly language.

    line 106
  9. Distinctive:

    If the response involves a commitment (timeline, refund, follow-up), note it in internal tracking.

    line 109
  10. Distinctive:

    Read the draft aloud to catch tone issues -- written words often sound harsher than intended.

    line 110

“Common” is measured: kept by at least 6 in 10 of the 3 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

Draft Customer Response

Draft a customer-facing response that is accurate, empathetic, and actionable. Adapt tone and structure to the situation type -- product questions, outage updates, bad news delivery, or feature declines.

Workflow

Step 1: Analyze the Inbound Message

Read the customer's message and classify the situation:

  • Situation type: Product question, bug report, outage inquiry, feature request, complaint, billing issue, account change.
  • Sentiment: Frustrated, neutral, confused, urgent, appreciative.
  • Complexity: Simple lookup vs. multi-part question vs. sensitive issue.
  • Relationship signals: Account tier, prior interactions, escalation history.
  • Implicit questions: What the customer is really asking beyond the literal words.

Step 2: Research the Answer

Gather the information needed to respond accurately:

  • Knowledge base: Search for relevant articles, docs, or FAQs.
  • Known issues: Check bug trackers or incident dashboards for related problems.
  • Account context: Subscription tier, feature entitlements, recent changes.
  • Prior communication: What has already been said to this customer about this topic.
  • Internal notes: Engineering updates, product decisions, timeline commitments.

Step 3: Select the Response Framework

Choose the appropriate structure for the situation:

SituationFramework
Product questionAcknowledge, Answer, Offer next steps
Bug reportValidate, Status update, Workaround if available, Timeline
Outage updateStatus, Impact, Actions taken, Next update time
Bad newsEmpathize, Explain reasoning, Offer alternative, Commit to follow-up
Feature declineThank, Explain why not now, Share what is planned, Invite feedback
Frustrated customerAcknowledge feeling, Take ownership, Concrete resolution, Prevention

Step 4: Draft the Response

Write the response following the selected framework. Adjust formality and length to match the channel (email, chat, ticket comment).

Output Format

## Draft Response

**Situation**: <type>
**Tone**: <empathetic / formal / casual / urgent>
**Channel**: <email / chat / ticket>

---

<Full draft response text>

---

**Internal Notes**
- Sources used: <KB articles, bug tickets, docs referenced>
- Follow-up needed: <any commitments made that require tracking>
- Escalation flag: <yes/no -- does this need manager review before sending?>

Examples

User: "Customer asks why their dashboard is loading slowly since last week" Action: Check for known performance issues, draft a response acknowledging the experience, explain the cause if known, provide a workaround and timeline.

User: "Customer requested Slack integration, we're not building it" Action: Draft a feature decline response that thanks the customer, explains prioritization reasoning without being dismissive, and points to the existing webhook alternative.

User: "Draft an outage update for the email delivery delay" Action: Write a concise status update with current impact, root cause summary, remediation steps taken, and next update time.

User: "Customer is angry about being charged after cancellation" Action: Draft an empathetic response acknowledging the billing error, confirming the refund, and explaining what steps have been taken to prevent recurrence.

Best Practices

  • Open by acknowledging the customer's experience before jumping to the solution.
  • Never blame the customer, even indirectly. Phrases like "as noted in our docs" read as condescending.
  • Be specific about timelines. "We'll look into it" is less reassuring than "Our team is investigating and I'll update you by Thursday."
  • Avoid jargon. Translate internal terms into customer-friendly language.
  • For bad news, lead with empathy and explain the reasoning -- customers accept "no" better when they understand why.
  • End with a clear next step: what you will do, what the customer should do, or when they will hear back.
  • If the response involves a commitment (timeline, refund, follow-up), note it in internal tracking.
  • Read the draft aloud to catch tone issues -- written words often sound harsher than intended.
  • For complex issues, break the response into numbered steps rather than dense paragraphs.
  • Match the customer's communication style. A casual customer gets a casual reply; a formal enterprise contact gets polished prose.

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.