agentleFS
NowistayNowistay/claude/skills/guest-records/SKILL.md

guest-records

Skill0 starsChanged 37 days agoMITView on GitHub

Review and maintain privacy-minimized Nowistay guest records. Use when a host asks to find a returning guest, review a guest's stay history, or add a guest to the customer base. Do not use merely because another booking or messaging workflow mentions a guest.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the minimum personal data needed for the host's explicit request.

    line 8
  2. Very specific:

    Use list_guests with a known name, a contact value already supplied by the user, or a property filter.

    line 12
  3. Very specific:

    Use get_guest with include_contact_details=false for booking totals and recent stays.

    line 14
  4. Distinctive:

    Never expose postal addresses, private notes, owner identifiers, or implementation fields.

    line 17
  5. Distinctive:

    Search by the supplied name first.

    line 21
  6. Distinctive:

    Never request payment-card or bank data, government identifiers, medical or biometric data, postal addresses, account passwords, access …

    line 23
  7. Very specific:

    Call create_guest_preview.

    line 24

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nowistay Guest Records

Use the minimum personal data needed for the host's explicit request.

Find and review

  1. Use list_guests with a known name, a contact value already supplied by the user, or a property filter. Do not ask for email or phone merely to search.
  2. Present the privacy-minimized list result. Do not imply that contact details are missing; they are intentionally omitted by default.
  3. Use get_guest with include_contact_details=false for booking totals and recent stays.
  4. Set include_contact_details=true only when the user explicitly asks for that guest's email or phone for a legitimate rental operation.

Never expose postal addresses, private notes, owner identifiers, or implementation fields. Keep internal guest IDs out of conversational responses unless needed to disambiguate records.

Add a guest

  1. Search by the supplied name first. If an existing record may be the same person, ask the user to disambiguate instead of creating a likely duplicate.
  2. Collect only the fields the user wants to store. A name alone is sufficient; email, phone, and language are optional.
  3. Never request payment-card or bank data, government identifiers, medical or biometric data, postal addresses, account passwords, access tokens, private notes, or unrelated personal information.
  4. Call create_guest_preview. If it returns duplicate=true, use the existing privacy-minimized guest record and do not create another one.
  5. Summarize exactly which fields will be stored. If the user asked only for a proposal, stop at the preview. If the user explicitly asked to add the guest, call create_guest_confirm with only the approval token.

There is no guest update or delete tool in this workflow. Do not simulate those actions with booking tools.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.