This is taking longer than expected.

Try againBrowse the library
AI Blocks

AI Blocks › Help your customers

Gorgias ticket tag planner

Use a Composio setup linked to Gorgias. It reads the available tags and returned ticket text, then suggests labels for topic, issue type and urgency. You get reasons and high, medium or low confidence labels for review. Those labels are judgments, not measured probabilities. Applying tags needs your approval and a supported update tool.

Review a Gorgias ticket or batch. Get suggested tags, reasons and confidence labels to check before approving any changes.

Free · No account · MIT licence · Made by Composio · Tested · Updated 28 Oct 2026

What you get

What goes in

  • A Gorgias ticket number, or the word batch for untagged tickets
  • Your Gorgias account connected through the Composio CLI

Before you start

  • An AI that can run commands and read skill files
  • The Composio CLI installed, with your Gorgias account linked

What comes out

  • Available Tags in System: The full list of tags already set up in your Gorgias account.
  • Tagging Recommendations: A table with ticket ID, subject, suggested tags, confidence level and the reason for each pick.
  • Summary: Counts of tickets checked, and how many are high, medium or low confidence.
  • Apply question: A question asking which suggested tags you want applied. Nothing changes until you say yes.

Is it for you?

Use it when

  • Your support queue has tickets with no tags.
  • A ticket has only one tag and may need more.
  • You want a second opinion on tags before a busy week.

Skip it when

  • You want to tag a ticket by pasting text outside Gorgias: ask your AI to suggest tags from the pasted text, then add them by hand.
  • Your tickets already have the right tags: leave them as they are, or fix the few wrong ones by hand in Gorgias.
  • You want to reply to customers: write the reply yourself or ask your AI to draft it, as this tool only suggests tags.

Similar items and how they differ

These do a similar job. Not sure which one? Try the one marked Start here.

ItemWhat it doesYou giveYou get
Gorgias duplicate ticket finder Start hereReview recent Gorgias tickets for likely duplicates or related issues. Get match reasons and suggested primary tickets to check before merging.
  • Your last 50 to 100 open or pending Gorgias tickets
  • Customer email, subject, first message, tags and creation date for each ticket
  • Strong Matches
  • Weak Matches
  • Stats
Gorgias ticket tag planner (this page)Review a Gorgias ticket or batch. Get suggested tags, reasons and confidence labels to check before approving any changes.
  • A Gorgias ticket number, or the word batch for untagged tickets
  • Your Gorgias account connected through the Composio CLI
  • Available Tags in System
  • Tagging Recommendations
  • Summary

Fill it in

Add what this task works from, then copy the request.

  • A ticket number, or the word batch for untagged tickets.
  • Your Gorgias account, connected to your AI.

Run it

Download the complete instructions and supporting files. Add them to Claude, ChatGPT or Gemini once, then ask for it by name in any chat. Pasting the instructions into a chat works too.

Download all files

Before and after this skill

Choose the steps you need. Bring your own material when you have it.

Before

Bring the material listed under Fill it in.

This skill

Gorgias ticket tag planner

Open builder

After

Details

From Composio. See the original on GitHub; shared under its licence, with a plain name for this library.

What goes in and out

You give it

  • A ticket number, or the word batch for untagged tickets.
  • Your Gorgias account, connected to your AI.

You get

  • A list of the tags you already use in Gorgias.
  • Suggested tags for each ticket, with a reason.
  • A confidence level for each ticket: high, medium or low.
  • A count of how many tickets need a manual look.

Use it when

  • Your support queue has tickets with no tags.
  • A ticket has only one tag and may need more.
  • You want a second opinion on tags before a busy week.
  • A new teammate needs to see how your tags are used.

More for Help your customers

Every help your customers skill

How the task works

  • Read your tag list. Read the tags already set up in Gorgias so suggestions use your own labels.
  • Match messages to tags. Read the ticket topic, issue, urgency, and customer group. Explain each suggested label.
  • Review proposed changes. Show the tag table and ask which changes you want to apply.

Full instructions

  • Use an AI that can run commands and read files. Install the Composio CLI first, and check its current pricing, since it may need a paid plan.
  • Link your Gorgias account when asked. The command is composio link gorgias.
  • Add the skill folder to your AI and ask for the auto-tag skill.
  • Give it one ticket number, or say batch to check untagged tickets.
  • Read the table. Check the medium and low confidence rows first.
  • Say which tags to apply. The skill does not change anything until you confirm.

Full instruction file

Auto-Tag Tickets

You are a ticket classification engine. Analyze untagged or under-tagged Gorgias tickets, determine the correct tags based on content, and suggest (or apply) them.

The user's input is: $ARGUMENTS

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 tickets from Gorgias filtered by tags" "get ticket details from Gorgias" "list all available ticket tags in Gorgias" in Bash.

Step 2: Get available tags

Run composio execute GORGIAS_LIST_TICKET_TAGS -d '{}' in Bash to get the full set of tags configured in the system. If the CLI reports the toolkit is not connected, ask the user to run composio link gorgias and retry.

Step 3: Fetch tickets
  • If a specific ticket ID was given: run composio execute GORGIAS_GET_TICKET -d '{"ticket_id":"<ID>"}' in Bash
  • If "batch" or no argument: run composio execute GORGIAS_LIST_TICKETS -d '<JSON>' in Bash, filtering for untagged tickets with the argument names from the schema (run composio execute GORGIAS_LIST_TICKETS --get-schema first if you do not have them)
Step 4: Classify each ticket

For each ticket, read the subject + message body and determine:

  • Primary tag (the main topic)
  • Secondary tags (additional relevant labels)
  • Confidence (High/Medium/Low)

Classification categories to consider:

  • Product area (billing, auth, integrations, API, UI, mobile, etc.)
  • Issue type (bug, question, feature-request, complaint, praise)
  • Urgency indicators (outage, blocking, data-loss)
  • Customer segment (enterprise, startup, free-tier)
Step 5: Present recommendations
## Auto-Tag Results

### Available Tags in System
[list them]

### Tagging Recommendations
| Ticket ID | Subject | Recommended Tags | Confidence | Reasoning |
|-----------|---------|-----------------|------------|-----------|
| #123 | "Can't login" | auth, bug | High | Customer reports 403 error on login |
| ... | | | | |

### Summary
- Tickets analyzed: X
- High confidence: X
- Medium confidence: X (review recommended)
- Low confidence: X (manual review needed)

Ask the user if they'd like to apply any of the suggested tags. Do NOT apply tags without explicit confirmation.

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: