Reply Triage

SkillCommunication

Classify inbound sales replies and route to auto-response, task, escalation, or suppression. Use when a new inbound message arrives.

Available today. Use it from your connected AI after setup.

No other account needed.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Reply Triage skill

What this skill tells your AI

The instructions your AI receives, as published by kami-community/kami in skills/reply_triage/SKILL.md and read by ahel’s review.

Load full conversation thread and account/contact context.
Classify message into one label:
- positive — interest, wants to learn more, agrees to call
- objection — not fit, timing, competitor, budget pushback
- information_request — asks for deck, pricing, security docs
- referral — points to another contact
- not_now — polite deferral with future potential
- unsubscribe — explicit opt-out
- negative — hostile or clear rejection
- spam_risk — automated or suspicious
Set escalation_required for: positive with buying intent, pricing/legal/security, complaints, unclear consent.
Update account pipeline_stage: engaged on any human reply; qualified on positive; suppressed on unsubscribe.
Create SalesTask or SalesNotification per escalation rules.
Optional bounded draft only for simple information_request with approved FAQ content.

ReplyClassification + side effects (task, notification, suppression).

Advanced