Gorgias duplicate ticket finder

What goes in and out

You give it

• Recent open or pending Gorgias tickets (the last 50 to 100 are checked).
• Your Gorgias account connected through Composio CLI.

You get

• Groups of likely duplicate tickets, each with the reason it matched.
• A suggested primary ticket for each group, the older one.
• A separate list of tickets that are only related.
• A count of tickets scanned and duplicate groups found.

How the task works

• Read recent tickets. Fetch recent open and pending tickets and collect customer, subject, message, tags, and dates.
• Compare shared details. Use matching customers, similar messages, close dates, shared errors, and order references as clues.
• List groups for review. Separate likely duplicates from related issues and explain each match. It does not merge tickets.

Full instructions

• Add the downloaded folder to an AI that can read skill files and run commands.
• Install Composio CLI. If Gorgias is not connected, run composio link gorgias when your AI asks.
• Ask your AI to find duplicate tickets in Gorgias, or to read SKILL.md and follow it.
• Read each group and its reason. Check the tickets in Gorgias before you act.
• Merge the tickets by hand in Gorgias. The tool never merges or sends anything.

Full instruction file

Duplicate Ticket Finder

Before you start: this needs the Composio CLI and a Gorgias account connected through it. Composio or Gorgias may need a paid plan, so check their pricing first. If either is missing, stop and say so.

You are a ticket deduplication specialist. Scan recent Gorgias tickets to find duplicates or closely related tickets from the same customer or about the same issue.

Before you start

Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait.

What you need (use your own material or the linked skill):

• Your question (yours): the decision or problem, and what a good outcome looks like.
• A tool connection (yours): an AI connected to an outside tool or service, such as an MCP server.

How to start:

1. Look first. Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name.
2. Check what's missing. Look for your question, a tool connection. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps.
3. Do the job. Follow the skill below with the facts and tools you have. Mark each gap with MISSING: where it belongs and never invent a fact to fill it.

Tools that do this best:

• Gorgias: Live lookups need Composio CLI access and connected accounts for these services.

Workflow

Step 1: Discover tools

Run composio search "list recent support tickets from Gorgias" "get ticket details from Gorgias" in Bash.

Step 2: Fetch recent tickets

Run composio execute GORGIAS_LIST_TICKETS -d '{...limit 50-100, open/pending...}' in Bash to fetch the last 50-100 open/pending tickets. If the CLI reports the toolkit is not connected, ask the user to run composio link gorgias and retry.

Step 3: Get details for comparison

For each ticket, extract:

• Customer email
• Subject line
• First message content
• Tags
• Creation date

Run composio execute GORGIAS_GET_TICKET -d '{"ticket_id":"<ID>"}' in Bash (in parallel) for tickets where the list doesn't provide enough detail.

Step 4: Detect duplicates

Apply these matching heuristics. Use these meanings: "similar subject (>70% overlap)" means more than 70% of the meaningful words in the two subjects are the same. "Rare error message" means an error text that appears in only a few tickets in this batch. "Near-identical" means the same text apart from names, numbers or greetings. When unsure, call it a weak match, not a strong one.

Strong match (likely duplicate):

• Same customer email + similar subject (>70% overlap)
• Same customer email + same tags + created within 24h
• Different customers but near-identical subject + message body

Weak match (possibly related):

• Same customer email + different but related subjects
• Different customers + same rare error message or product area
• Tickets referencing the same order/account ID

Step 5: Present findings

## Duplicate Ticket Analysis

### Strong Matches (likely duplicates)
#### Group 1
| Ticket | Customer | Subject | Created | Status |
|--------|----------|---------|---------|--------|
| #123 | user@co.com | "Login broken" | 2h ago | Open |
| #119 | user@co.com | "Can't log in" | 5h ago | Open |
**Similarity:** Same customer, same issue (login), 3h apart
**Recommendation:** Merge #123 into #119 (keep older as primary)

#### Group 2
...

### Weak Matches (possibly related)
| Tickets | Reason | Recommendation |
|---------|--------|----------------|

### Stats
- Tickets scanned: X
- Duplicate groups found: X
- Estimated duplicates: X
- Potential time saved by merging: ~Xh (only if you can work it out from counts the user gave; otherwise leave it out)

Step 6: Next steps

Tell the user to open each group in Gorgias, check that the tickets really are the same issue, confirm which ticket is the primary one, and merge by hand.

Note: This skill identifies duplicates but does NOT auto-merge. Present findings for agent review.

After this

When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own:

• The Support issue cause investigator. It takes the audit report.
• The Escalation brief writer. It takes the audit report.
• The Support ticket help article writer. It takes the audit report. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.