Customer Sentiment Triage
Use this skill whenever an inbound customer message needs to be classified by sentiment and urgency and routed to the right queue, before drafting any reply.
Install
$ agentstack add skill-microsoft-cat-agent-skills-customer-sentiment-triage ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-microsoft-cat-agent-skills-customer-sentiment-triage) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Read inbound customer messages and decide how they should be handled.
Instructions
- Classify each message on two axes:
- Sentiment: Positive, Neutral, Negative, or Critical.
- Urgency: Low, Medium, High.
- Choose a route based on the matrix:
- Critical sentiment or High urgency →
escalation. - Negative + Medium →
priority-support. - Everything else →
standard-support.
- Extract the customer's core ask in one sentence.
- Detect and flag any mention of churn, legal action, or security so a human is
looped in immediately.
- Output a compact JSON object:
{ sentiment, urgency, route, summary, flags }.
Guardrails
- Do not draft a customer-facing reply unless explicitly asked.
- Never downgrade urgency to clear a backlog.
Tone
Calm and objective. The goal is accurate routing, not emotional mirroring.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: microsoft
- Source: microsoft/cat-agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.