Ticket pulse

Skill quivly/skills/customer-engineering/ticket-pulse

Production-ready Agent Skills for Customer Engineering, Post-Sales, and Customer Success teams. Quivly Skills is a curated open-source collection of reusable skills that give AI agents deep expertise in customer engineering workflows. Every skill follows the official Agent Skills specification.

Install

npx -y skills add quivly/skills --skill ticket-pulse

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

One thing to look at

4 stars4 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

Reads a customer's support health — open ticket load, recurring themes, aging issues, and escalation candidates. Use when asked "how is support going for X", before meetings with support-sensitive accounts, or when ticket friction might explain churn risk.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.5 KB, as published. Nobody here has run it

Ticket Pulse

You assess whether support experience is helping or hurting this customer relationship.

Core principle: volume is engagement; aging, repetition, and escalating severity are the risk.

Workflow

Load the customer record (get-customer) for tier and context — a P1 for an enterprise account 30 days from renewal is different from the same ticket at a small account.
Pull tickets for the customer (search-tickets), last 90 days. Bucket them:
- Open & aging — unresolved past a reasonable SLA
- Recurring themes — same feature or failure appearing repeatedly
- Severity pattern — are issues getting more serious over time?
Check surrounding conversations (search-conversations) for frustration that never became a ticket — often the loudest signal.
Check signals on record (get-insights) for support-related risk already flagged.

Output Format

Support pulse: {Customer} — one-line verdict: Healthy / Friction building / Escalation needed

The numbers — open count, oldest unresolved, volume trend vs. prior period

Themes — recurring issues grouped, each with occurrence count and current status

Sentiment check — what the customer's tone says beyond the tickets

Recommended actions — e.g., escalate ticket X to product, proactive check-in on theme Y, close-the-loop message on resolved-but-unacknowledged items

Guidelines

Volume alone isn't a red flag — an engaged customer files tickets. Aging, repetition, and severity escalation are the red flags.
Distinguish "customer is blocked" from "customer is annoyed" — different plays.
If there are zero tickets and low usage, flag disengagement, not health.

Related skills: friction has boiled over → escalation-brief; support friction is driving churn risk → churn-save-plan.