- Home
- Skills
- Business & Operations
- Support Response Drafter
Works with the AI Agents you already use
Support Response Drafter
Drafts empathetic, de-escalating customer support replies that avoid robotic corporate jargon.
$9
Support Response Drafter
Example session with this skill installed
Draft a reply to a customer, Sarah, who is angry because her package is 4 days late and she missed her sister's birthday. We don't have a tracking update yet, but I can offer a $10 credit.
- Read your context and instructions
- Compiled the support response drafter
I have analyzed the ticket and drafted a response that acknowledges the specific emotional impact of the delay while providing a concrete resolution.
Support Ticket Analysis & Draft
| Field | Detail |
|---|---|
| Ticket Summary | Late delivery resulting in missed event (birthday gift). |
| Emotional State | High frustration; feeling of letdown/disappointment. |
| Escalation Flag | No. Standard logistics delay with authorized compensation. |
Draft Response
Subject: Regarding your recent order
Hi Sarah,
I am so sorry that your package didn't arrive in time for your sister’s birthday. I know how much it sucks to show up empty-handed when you've planned ahead, and I truly regret that we let you down on such a special occasion.
I’ve checked the current status, and while I don’t have a new tracking update from the carrier just yet, I am monitoring this personally. I will send you a direct update as soon as the package is scanned at the next hub.
To help make up for the frustration and the delay, I’ve applied a $10 credit to your account which you can use on any future order. You should see a confirmation email for that credit within the next hour.
I’ll be in touch the moment I see movement on your delivery.
Best,
[Agent Name]
Internal Note
Reasoning: Acknowledged the specific event (birthday) to show the customer was heard. Avoided "sorry for the inconvenience" in favor of validating the disappointment. Provided a concrete $10 credit and a commitment to follow up once tracking updates.
Next steps
- Review the draft for brand voice alignment.
- Manually apply the $10 credit in the billing system.
- Set a reminder to check the tracking status in 12 hours.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Generic "sorry for the inconvenience" templates make frustrated customers feel ignored. Standard support scripts often fail to address the specific root cause or validate the customer's actual emotional state.
What it does
- Analyzes ticket text to identify the root cause and the customer's specific emotional state.
- Drafts de-escalation replies that avoid corporate deflection and robotic platitudes.
- Flags tickets for human escalation if they involve safety issues, legal threats, or unauthorized refund amounts.
- Uses placeholders for specific policy data to prevent inventing promises the company cannot keep.
Why this beats prompting it yourself
Most LLMs default to overly apologetic or "customer service voice" that triggers further frustration. This skill enforces specific de-escalation frameworks and strict anti-pattern checks to ensure replies sound human, empathetic, and resolution-oriented.
Use cases
- Drafting replies to angry customers about billing disputes or service outages.
- Responding to refund requests with firm but empathetic policy communication.
- Handling repeat complaints where the customer feels their previous issues were ignored.
- Training junior support staff on how to structure professional, warm communications.
Known limitations
Does not integrate directly with CRM/ticketing APIs. Not for crisis response involving safety-critical threats or self-harm.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Does not connect to external ticketing systems. User must provide specific refund/policy details or the skill will use placeholders. Not for high-stakes crisis management or safety threats.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago