agentleFS
NowistayNowistay/claude/skills/property-knowledge/SKILL.md

property-knowledge

Skill0 starsChanged 37 days agoMITView on GitHub

Maintain the private Nowistay AI co-host knowledge base for each property. Use to list, search, add, correct, or copy reusable property questions and answers such as policies, equipment details, access guidance, and local recommendations.

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
  1. Very specific:

    Use list_property_knowledge_questions with limit=100.

    line 15
  2. Very specific:

    Use get_property_knowledge_question only when one exact record needs verification before an update.

    line 16
  3. Distinctive:

    Check for an existing equivalent question before creating a new one.

    line 21
  4. Very specific:

    Use create_property_knowledge_question_preview for new Q&A and update_property_knowledge_question_preview for corrections.

    line 22
  5. Very specific:

    Use copy_property_knowledge_questions_preview with selected question_ids, or omit them to copy all source Q&As.

    line 29
  6. Distinctive:

    Use one multi-target copy rather than repeating one copy per property.

    line 31
  7. Distinctive:

    If the user asked only for a proposal, stop at the preview.

    line 33

≈ “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 Property Knowledge

Manage private Q&A knowledge separately from the public welcome guide.

Store reusable property facts, not guest records. Do not add guest names, contact details, booking references, message transcripts, private notes, payment data, government identifiers, medical or biometric data, account credentials, or other guest-specific information to the knowledge base.

Read and find

  1. Resolve source and target properties once with list_properties.
  2. Use list_property_knowledge_questions with limit=100; paginate only when needed. Use search to avoid loading the full knowledge base for a focused question.
  3. Use get_property_knowledge_question only when one exact record needs verification before an update.
  4. Present questions and answers conversationally. Keep internal IDs out of the response unless needed for disambiguation.

Add or update

  1. Check for an existing equivalent question before creating a new one.
  2. Use create_property_knowledge_question_preview for new Q&A and update_property_knowledge_question_preview for corrections.
  3. Preserve need_host unless the user explicitly changes whether future answers require host intervention.
  4. Summarize the exact question, answer, property, and host-review setting.

Copy between properties

  1. List the source Q&As first and resolve every target property.
  2. Use copy_property_knowledge_questions_preview with selected question_ids, or omit them to copy all source Q&As.
  3. Explain that copying is a safe merge: matching normalized questions are skipped and target knowledge is never deleted or replaced.
  4. Use one multi-target copy rather than repeating one copy per property.

If the user asked only for a proposal, stop at the preview. If the user explicitly requested the write, call the matching confirm tool with only the approval token. Do not expose vector-store or database implementation details.

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.