agentleFS
NowistayNowistay/claude/skills/calendar-revenue/SKILL.md

calendar-revenue

Skill0 starsChanged 37 days agoMITView on GitHub

Review and safely update Nowistay calendar availability, nightly rates, minimum or maximum stays, stop-sell rules, and arrival or departure restrictions. Use for pricing changes, bulk date-range updates, weekday rules, availability checks, and revenue-management tasks.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Read the current state before changing it, and change only fields the user requested.

    line 8
  2. Very specific:

    Call get_calendar_ari for each target property and exact date range.

    line 13
  3. Distinctive:

    Do not infer that a date is available from the absence of a booking alone.

    line 16
  4. Distinctive:

    Do not send availability, price, stay rules, or restrictions that the user did not ask to modify.

    line 21
  5. Very specific:

    Use update_calendar_ari_preview once per property.

    line 22
  6. Very specific:

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

    line 24
  7. Distinctive:

    Do not silently convert currencies or copy one property's absolute rate to properties using another currency.

    line 30
  8. Distinctive:

    Do not close dates, set stop-sell, or change arrival/departure restrictions unless explicitly requested.

    line 31
  9. Distinctive:

    When the request is ambiguous between a percentage change and an absolute rate, ask one focused clarification before staging.

    line 32

≈ “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 Calendar and Revenue

Read the current state before changing it, and change only fields the user requested.

Review

  1. Resolve the target properties once with list_properties.
  2. Call get_calendar_ari for each target property and exact date range.
  3. Summarize current availability, rates, and stay rules. Keep property currencies separate and preserve local dates.

Do not infer that a date is available from the absence of a booking alone. Use calendar availability as the source of truth.

Update

  1. Translate the request into an exact property, date range, optional weekdays, and only the fields to change.
  2. Do not send availability, price, stay rules, or restrictions that the user did not ask to modify.
  3. Use update_calendar_ari_preview once per property. For weekday updates, use 0=Monday through 6=Sunday and never send an empty days_of_week list.
  4. Summarize the staged changes by property, dates, weekdays, rate, and rules.
  5. If the user asked only for a proposal or preview, stop. If the user explicitly asked to apply the change, call update_calendar_ari_confirm with only the approval token returned by the preview.

For portfolio-wide updates, collect one approval token per property and confirm each token exactly once. Never rebuild the update payload during confirmation.

Guardrails

  • Do not silently convert currencies or copy one property's absolute rate to properties using another currency.
  • Do not close dates, set stop-sell, or change arrival/departure restrictions unless explicitly requested.
  • When the request is ambiguous between a percentage change and an absolute rate, ask one focused clarification before staging.
  • Report partial failures per property without repeating successful updates.

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.