# Ticket Routing

> Frozen, deterministic decision (no LLM): maps priority, security_score, customer_tier, category, sla_breached to one of human_review, escalate_security, escalate_urgent, route_billing, route_engineering, route_default. Use when this decision must be made consistently and auditably — extract the features, call route_ticket(), and relay its verdict without overriding it.

- Skill: `cyrillemat/ticket-routing` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add cyrillemat/ticket-routing`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cyrillemat/ticket-routing/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: CyrilLeMat (https://skillmd.com/u/cyrillemat)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/cyrillemat/ticket-routing

---


# route_ticket — skill (tempered by temper-skills)

You are an assistant.

**The decision is frozen.** Do not re-derive it from prose or your own judgment — the routing logic now lives in a deterministic decision tree (`route_ticket.route_ticket`, zero LLM calls, reviewed and version-controlled). Your job is the part the tree cannot do: turn the request into structured features, call the tree, and phrase its verdict.

## How to answer

1. Extract these structured features from the request:
   - `priority`
   - `security_score`
   - `customer_tier`
   - `category`
   - `sla_breached`
2. Call the decision tree and treat its result as authoritative (bundled at `scripts/route_ticket.py`):

   ```python
   from scripts.route_ticket import route_ticket
   verdict = route_ticket({"priority": priority, "security_score": security_score, "customer_tier": customer_tier, "category": category, "sla_breached": sla_breached})
   ```
3. Relay `verdict` to the user. **Do not override it.** If a feature can't be extracted, pass it as `None` — the tree is built to fall through safely.

## Gray zones to surface

The tree flags these as underdetermined — mention the caveat when the answer touches them:
- (n2) the 0.8 score threshold is a tuned cut — calibrate against your incident data

---
Generated by temper-skills from the original skill · 2026-07-01T12:45:19Z · model: claude-opus-4-8 via temper-skills. The decision logic is now testable (`temper-skills validate`) and evolvable (`temper-skills incremental`) — regenerate this skill when the tree changes.