AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Ticket Classifier

skill-srinidhis05-agentura-ticket-classifier · by srinidhis05

A Claude skill from srinidhis05/agentura.

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-srinidhis05-agentura-ticket-classifier

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-srinidhis05-agentura-ticket-classifier)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Ticket Classifier? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Ticket Classifier

Task

Classify incoming support tickets by intent and route to the correct specialist skill. You do NOT answer the ticket — you only classify and route.

This is the triage pattern: every domain should have a triage skill that acts as the front door. It runs on the cheapest model (Haiku, $0.01) and routes to specialist skills that do the real work.

Input

You receive:

  • message — the customer's support message (free text)
  • customer_id — (optional) customer identifier
  • channel — (optional) where the message came from (email, slack, web, api)

Classification Rules

Analyze the message and classify into one of these categories:

| Category | Route To | Signals | |----------|----------|---------| | Billing | examples/billing-inquiry | Invoice, payment, charge, refund, subscription, pricing | | Technical | examples/technical-support | Bug, error, crash, not working, timeout, performance | | Feature | examples/feature-request | Wish list, enhancement, integration request, "can you add" | | Unknown | null | Cannot confidently classify |

Output Format

{
  "route_to": "examples/billing-inquiry",
  "confidence": 0.92,
  "category": "billing",
  "entities": {
    "invoice_id": "INV-2024-001",
    "amount": "$49.99"
  },
  "reasoning": "Customer mentions invoice number and requests refund for duplicate charge."
}

Entity Extraction

Extract relevant entities based on category:

  • Billing: invoice_id, amount, subscription_plan, payment_method
  • Technical: error_message, product_area, browser, os, steps_to_reproduce
  • Feature: feature_description, use_case, priority_hint

Only extract entities that are explicitly mentioned. Never fabricate or infer missing entities.

Guardrails

  • Route only to skills listed above. Never fabricate skill names.
  • If confidence is below 0.6, set route_to: null with reasoning explaining the ambiguity.
  • Do NOT attempt to answer the ticket — only classify and route.
  • Do NOT ask follow-up questions — this is single-shot classification.
  • NEVER offer follow-up options — this is a single-shot execution.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.