guest-messaging
Skill0 starsChanged 37 days agoMITView on GitHub
Find guest conversations, read recent messages, summarize context, draft replies, and send messages through Nowistay. Use for "show the last messages", "reply to this guest", booking-based conversation lookup, follow-up replies, and multilingual guest communication.
In this repository8 other files it gives its agents.
- calendar-revenueSkill
- daily-briefSkill
- direct-bookingsSkill
- guest-recordsSkill
- portfolio-reportingSkill
- property-knowledgeSkill
- team-operationsSkill
- welcome-guideSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep the conversation natural and hide implementation details from the host.
- Very specific: line 13
Use list_threads with booking_id when a booking is known.
- Very specific: line 14
Use get_thread_messages once with the exact requested message count.
- Very specific: line 23
Use send_guest_message_preview with either thread_id or booking_id, never both.
- Very specific: line 25
If the user asked only for a draft, stop before the preview or after staging as appropriate.
- Distinctive: line 27
Do not recommend switching to personal email or phone merely because no conversation was found.
- Distinctive: line 29
Never copy sensitive or guest-specific message content into a welcome guide, property knowledge base, mission, or booking note unless the …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nowistay Guest Messaging
Keep the conversation natural and hide implementation details from the host.
Find and read
- Resolve a guest or booking with
list_guests,list_bookings, orget_bookingusing information already supplied by the user. Prefer a booking reference, property plus stay dates, or name. Do not ask for email or phone merely to disambiguate when operational context can identify the stay. - Use
list_threadswithbooking_idwhen a booking is known; otherwise narrow by property. - Use
get_thread_messagesonce with the exact requested message count. Preserve chronology when presenting the exchange. - For a follow-up such as "tell them...", reuse the guest and conversation already established in the current task unless it became ambiguous.
Say "I did not find a conversation" when none exists. Do not mention missing thread IDs, channel IDs, database records, or other private implementation details. Do not retrieve or expose a guest's email, phone, postal address, private notes, or unrelated booking data unless the host explicitly asks for the specific information and it is needed for the requested operation.
Draft and send
- Base the reply on the actual conversation, booking, and property context. Do not invent policies, promises, prices, or availability.
- Match the guest's language and the host's requested tone. Keep the reply ready to send, without technical commentary.
- Use
send_guest_message_previewwith eitherthread_idorbooking_id, never both. If no conversation exists but a booking is known, usebooking_id; Nowistay can prepare the appropriate conversation through its existing flow. - Show the recipient in conversational terms and the exact message.
- If the user asked only for a draft, stop before the preview or after staging as appropriate. If the user explicitly asked to send, call
send_guest_message_confirmwith only the approval token.
Do not recommend switching to personal email or phone merely because no conversation was found. First use the booking-based Nowistay send flow when available.
Never copy sensitive or guest-specific message content into a welcome guide, property knowledge base, mission, or booking note unless the user explicitly requests that exact transfer and the content is appropriate for the destination.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

