agentleFS
NowistayNowistay/claude/skills/portfolio-reporting/SKILL.md

portfolio-reporting

Skill0 starsChanged 37 days agoMITView on GitHub

Build privacy-minimized Nowistay financial and operational reports across many properties. Use for CSV or spreadsheet exports, revenue and fee totals, OTA commissions, cleaning costs, team-member billing, workload reports, owner statements, and booking-to-mission reconciliation.

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:

    Call list_bookings with response_format=table, include_details=false, limit=500, and offset=0.

    line 14
  2. Very specific:

    Call list_missions in the same table mode only when the report needs cleaning, operations, assignments, workload, or team-member data.

    line 16
  3. Very specific:

    Never restart the extraction property by property unless the user explicitly requests separate queries or the server requires it.

    line 19
  4. Distinctive:

    Do not call tools with contact-detail or private-note include flags for aggregate reporting.

    line 25
  5. Distinctive:

    Keep currencies separate. Never sum EUR and USD into one total.

    line 30
  6. Distinctive:

    Keep cancelled or unavailable bookings separate from active revenue unless the user defines another rule.

    line 31
  7. Very specific:

    Do not claim data is truncated when hasMore=false and all pages were collected.

    line 41

≈ “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 Portfolio Reporting

Favor complete table-shaped extraction over repeated detailed calls.

Collect data

  1. Confirm the requested date range, portfolio scope, grouping dimensions, and output format. Infer obvious values from the prompt instead of asking unnecessary questions.
  2. Resolve properties once with list_properties. Omit property_ids from later list calls when the user wants every eligible property.
  3. Call list_bookings with response_format=table, include_details=false, limit=500, and offset=0.
  4. Append each page's rows under the returned columns. Continue with resultMetadata.nextOffset while resultMetadata.hasMore=true.
  5. Call list_missions in the same table mode only when the report needs cleaning, operations, assignments, workload, or team-member data.
  6. Join booking and mission rows with bookingId when combining finances and operations. Use property IDs only as a secondary key.

Never restart the extraction property by property unless the user explicitly requests separate queries or the server requires it. Never use get_booking, get_mission, or include_details=true for a bulk export.

Minimize personal data

  • Select and retain only the source columns needed for the requested report.
  • Exclude guest names, contact details, reservation references, message content, private notes, and mission descriptions from financial, owner, billing, and workload reports unless the user explicitly requests a specific field and it is necessary for that report.
  • Do not call tools with contact-detail or private-note include flags for aggregate reporting.
  • Team-member names may be included when the user requests assignment, workload, or billing by team member. Do not include their contact details.

Calculate and verify

  • Keep currencies separate. Never sum EUR and USD into one total.
  • Keep cancelled or unavailable bookings separate from active revenue unless the user defines another rule.
  • Preserve source columns in the detailed sheet and add calculated summary sheets or tables.
  • Support grouping by property, team member, mission type, booking channel, status, month, or currency.
  • Reconcile row counts against pagination metadata before reporting completion.
  • State filters, exclusions, currency handling, and any missing source values in the result.

Deliver

For a requested CSV or spreadsheet, create the file from the complete concatenated rows. Include a readable summary plus a privacy-minimized detail sheet containing only the columns needed to audit the totals. If the user only asks a question, return the totals directly without creating a file.

Do not claim data is truncated when hasMore=false and all pages were collected.

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.