Gorgias support metrics reporter

What goes in and out

You give it

• The dates you want to review.
• Access to your Gorgias tickets, linked through Composio.
• Your Google account linked through Composio (optional). The skill also looks in your Google Drive for an existing Support Metrics sheet before it makes a new one, so it needs Google Drive access too.

You get

• Ticket counts by status, plus new tickets in the last day and week.
• Average and median first response time, and average resolution time.
• Tables of tickets by category and by tag.
• A volume trend, a response time trend, and the busiest day.
• The most common issue and the longest open ticket.
• A Google Sheet with the report, if you ask for it.

How the task works

• Choose the date range. Read ticket records for the chosen dates within the skill's stated collection limits.
• Measure the sample. Use a sample of full threads for response times. Keep sampled measures separate from whole-queue counts.
• Prepare the report. Show volume, response times, issue groups, trends, and notable tickets. Offer a Google Sheets export.

Full instructions

• Use an AI that can run commands and read skill files, such as Claude Code. A plain chat window cannot run this.
• Install Composio CLI and link your accounts. Run composio link gorgias, and link Google Sheets if you want the export.
• Add the downloaded folder to your AI and ask it to run the support metrics skill.
• Tell it the dates to review.
• Check the sample note. Counts cover the first 100 tickets in your dates, so a busy period is cut off. Response times come from up to 20 tickets, the most recently created ones.
• Say yes if you want the Google Sheet. The sheet holds customer ticket data, so share it with care.
• Use the result in your weekly team review. Share the Highlights and Trends sections, and use the Gorgias weekly support report and the Gorgias support queue action planner to turn the numbers into next steps.

Full instruction file

Support Metrics Dashboard

You are a support analytics specialist. Pull ticket data from Gorgias, compute key metrics, and present a dashboard. Optionally export to Google Sheets.

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 your Gorgias account linked through Composio.
• Google Sheets and Google Drive: Only for the optional export. Link your Google account through Composio. The skill looks in Drive for an existing sheet first.

Workflow

Step 1: Discover tools

Run composio search "list all support tickets from Gorgias with filtering by date" "get ticket details and tags from Gorgias" "create or update a Google Sheet with data" in Bash.

Step 2: Get tool schemas

Run composio execute <SLUG> --get-schema in Bash (in parallel) for:

• GORGIAS_LIST_TICKETS
• GORGIAS_GET_TICKET
• GORGIAS_LIST_TICKET_TAGS
• GOOGLESHEETS_CREATE_GOOGLE_SHEET1
• GOOGLESHEETS_BATCH_UPDATE
• GOOGLEDRIVE_FIND_FILE

Step 3: Fetch ticket data

Run composio execute GORGIAS_LIST_TICKETS -d '<JSON>' in Bash to pull tickets for the dates the user gave, using the argument names from the schema you fetched in Step 2. Paginate through results, but stop at 100 tickets for the reporting period. This means every count below covers at most the first 100 tickets, not the whole period. If the period holds more, say so and show the figure as "first 100 tickets". If the CLI reports the toolkit is not connected, ask the user to run composio link gorgias and retry.

Step 4: Enrich with details

Choose the sample as the 20 most recently created tickets in the period (or all of them if there are fewer), and say so in the report. Calculate first response time as the time from the customer's first message to the first reply from an agent, and resolution time as the time from the first message to the closing time, both read from message timestamps. For each sampled ticket, run composio execute GORGIAS_GET_TICKET -d '{"ticket_id":"<ID>"}' in Bash as parallel calls to get message-level data for response time calculations.

Step 5: Compute metrics

Calculate and present:

## Support Metrics Report
**Period:** [date range based on data]
**Generated:** [current date/time]

### Volume
- Total Tickets: X (this is the capped count of up to 100 tickets, not the full total for the period; say "100+ in the period" if you hit the cap)
- Open: X | Pending: X | Closed: X
- New (last 24h): X
- New (last 7d): X

### Response Performance
- Sample note: volume counts cover up to 100 tickets in the period; the times below come from a sample of up to 20 tickets, so treat them as a rough guide, not a full-queue figure. State the real counts.
- Avg First Response Time: Xh Xm (sample)
- Median First Response Time: Xh Xm (sample)
- Avg Resolution Time: Xh Xm (sample)

### Breakdown by Category
| Category | Count | % | Avg Resolution |
|----------|-------|---|----------------|

### Breakdown by Tag
| Tag | Count | % |
|-----|-------|---|

### Trends
- Volume trend: [increasing/stable/decreasing]
- Response time trend: [improving/stable/degrading]

### Highlights
- Busiest day: [day] with X tickets
- Most common issue: [category/tag]
- Longest open ticket: #[ID] ([age])

Step 6: Export to Google Sheets (if requested)

If the user wants to export:

1. Run composio execute GOOGLEDRIVE_FIND_FILE -d '{"name":"Support Metrics"}' in Bash to check for an existing sheet
2. Parse the JSON output. If not found, run composio execute GOOGLESHEETS_CREATE_GOOGLE_SHEET1 -d '{"title":"Support Metrics"}' in Bash and extract the sheet ID
3. Run composio execute GOOGLESHEETS_BATCH_UPDATE -d '{"spreadsheet_id":"<id>","data":[...]}' in Bash to write headers and data rows
4. Share the sheet link with the user

Ask the user: "Would you like me to export this to a Google Sheet?"

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 Gorgias weekly support reporter.
• The Gorgias support queue action planner. 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.