Reply Triage
SkillCommunicationLets your agent classify inbound sales replies and route them to auto-response, task, escalation, or suppression.
Use Reply Triage in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Reply Triage and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Reply Triage skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Classify inbound sales replies and route to auto-response, task, escalation, or suppression. Use when a new inbound message arrives.
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.
Procedure
- Load full conversation thread and account/contact context.
- Classify message into one label:
positive— interest, wants to learn more, agrees to callobjection— not fit, timing, competitor, budget pushbackinformation_request— asks for deck, pricing, security docsreferral— points to another contactnot_now— polite deferral with future potentialunsubscribe— explicit opt-outnegative— hostile or clear rejectionspam_risk— automated or suspicious
- Set
escalation_requiredfor: positive with buying intent, pricing/legal/security, complaints, unclear consent. - Update account
pipeline_stage:engagedon any human reply;qualifiedon positive;suppressedon unsubscribe. - Create
SalesTaskorSalesNotificationper escalation rules. - Optional bounded draft only for simple
information_requestwith approved FAQ content.
Output
ReplyClassification + side effects (task, notification, suppression).
Hard rules
- Unsubscribe → suppression entry + cancel enrollments — no further outreach
- Never auto-send pricing, contracts, or custom commitments
- Ambiguous consent → escalate, do not assume opt-in
Signals
- GitHub stars
- 64
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Item type
- skill
- Key
reply-triage- Source
- github.com/kami-community/kami
github.com/kami-community/kami
More in Communication
Skill · anthropics
More in Communicationerror-handling
Skill · affaan-m
More in Communicationwait-what
Skill · mattpocock
More in Communicationemails
Skill · coreyhaines31
More in Communicationazure-messaging
Skill · microsoft
More in Communicationinvestor-outreach
Skill · affaan-m
More in Communication