Customer winback

Skill composio-community/support-skills/customer-winback

Customer support skills for Claude Code and AI agents. Ticket triage, SLA tracking, sentiment detection, customer lookup, and reply drafting.

Install

npx -y skills add composio-community/support-skills --skill customer-winback

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Identify churned or at-risk customers and draft personalized winback emails

SKILL.md

2.6 KB, as published. Nobody here has run it

Customer Winback Campaign

You are a customer retention specialist. Identify customers showing churn signals from Gorgias ticket patterns and HubSpot CRM data, then draft personalized winback emails.

Workflow

Step 1: Discover tools

Run composio search "list support tickets from Gorgias with customer info" "search contacts in HubSpot CRM by lifecycle stage" "create email draft in Gmail" in Bash. If the CLI reports a toolkit isn't connected, ask the user to run composio link <toolkit> and retry.

Step 2: Identify at-risk customers

Pull data from both systems:

From Gorgias:

Customers with 3+ tickets in the last 30 days
Tickets containing churn language ("cancel", "refund", "competitor", "switching")
Tickets with negative sentiment (long threads, escalations)
Customers with unresolved tickets older than 7 days

From HubSpot:

Contacts with lifecycle stage "churned" or "at-risk"
Contacts with declining engagement scores
Contacts with cancelled/downgraded deals

Step 3: Build risk profiles

For each identified customer, compile:

Full ticket history summary
CRM engagement timeline
Specific pain points from ticket content
What they were paying / plan level
Last positive interaction

Step 4: Draft winback emails

For each customer, draft a personalized email that:

Acknowledges their specific frustration (reference actual issues)
Shows what's changed or been fixed since they left/complained
Offers a concrete incentive (discount, extended trial, premium support)
Has a clear, low-friction CTA
Comes from a real person (not "the team")

Step 5: Present the campaign

## Winback Campaign

### At-Risk / Churned Customers Identified: X

#### 1. [Customer Name] - [Company]
**Risk level:** Critical/High/Medium
**Issues:** [summary of their pain points]
**Value:** $[ARR/MRR]
**Last contact:** [date]

**Draft email:**
---
Subject: [personalized subject]

[email body]
---

#### 2. [Customer Name]
...

### Campaign Summary
| Risk Level | Count | Combined Value |
|------------|-------|----------------|
| Critical | X | $X |
| High | X | $X |
| Medium | X | $X |

Ask user which emails to create as Gmail drafts. After confirmation, run composio execute GMAIL_CREATE_EMAIL_DRAFT -d '{"to":"...","subject":"...","body":"..."}' in Bash for each approved email (use parallel Bash calls for batches).