team-operations
Skill0 starsChanged 37 days agoMITView on GitHub
Plan and manage Nowistay cleaning, maintenance, urgency, and custom missions. Use for mission lists, team workloads, assignments, scheduling, completion status, mission reports, cleaning plans, and operational follow-up across one or many properties.
In this repository8 other files it gives its agents.
- calendar-revenueSkill
- daily-briefSkill
- direct-bookingsSkill
- guest-messagingSkill
- guest-recordsSkill
- portfolio-reportingSkill
- property-knowledgeSkill
- welcome-guideSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use summaries for planning and retrieve full details only for the missions that need action.
- Very specific: line 13
Use list_missions with the smallest useful filters: property, booking, status, type, team member, or start date.
- Very specific: line 15
Use get_mission for one selected mission and get_mission_report only when completion comments, checklist results, or photos are needed.
- Very specific: line 17
Do not retrieve every mission report for a list.
- Very specific: line 22
Use an ISO 8601 scheduled_at with timezone.
- Distinctive: line 25
If the user explicitly asked to apply the action, call the matching confirm tool with only its approval token.
- Very specific: line 27
Use silent_update=true only when the user explicitly wants to avoid normal team notifications.
- Distinctive: line 29
Keep mission titles, descriptions, and notes strictly operational.
≈ “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 Team Operations
Use summaries for planning and retrieve full details only for the missions that need action.
Review operations
- Resolve properties once with
list_propertieswhen names are used. - Use
list_missionswith the smallest useful filters: property, booking, status, type, team member, or start date. - For portfolio-wide exports or workload analysis, use
response_format=table,include_details=false,limit=500, and followresultMetadata.nextOffsetuntilhasMore=false. - Use
get_missionfor one selected mission andget_mission_reportonly when completion comments, checklist results, or photos are needed.
Do not retrieve every mission report for a list. Trust resultMetadata.hasMore to decide whether a list is complete.
Create or update
- For creation, provide
mission_typeand either a property or booking. Resolve the property from the booking when possible. - Use an ISO 8601
scheduled_atwith timezone. Do not guess a team member ID; if it cannot be resolved reliably from current data, ask the user or leave the mission unassigned. - Stage creation with
create_mission_previewor changes withupdate_mission_preview. - Summarize property, booking context when needed, type, schedule, assignment, status, and notification behavior. Include a guest name only when the user requested it or the identity is necessary for the mission.
- If the user explicitly asked to apply the action, call the matching confirm tool with only its approval token. Otherwise stop at the preview.
Use silent_update=true only when the user explicitly wants to avoid normal team notifications. Report partial failures without repeating successful actions.
Keep mission titles, descriptions, and notes strictly operational. Do not add guest contact details, medical or biometric data, payment information, government identifiers, account credentials, or unrelated personal information.
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.

