agentleFS
AppFreeticketAppFreeticket/freeticket-mcp/skills/show-day-close/SKILL.md

show-day-close

Skill0 starsChanged 4 months agoMITView on GitHub

Close out a FreeTicket show day with the FreeTicket MCP tools — live attendance, the access-close record, attendance vs. capacity, sales and revenue of the date, stuck payments, attendee export and settlement status. Use when the user asks for the end-of-night/show-day report, the "cierre" or "acta de cierre de acceso" of an event date, or how a show went.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only unless the human asks for an action.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Show-day close

Read-only unless the human asks for an action. Ask for the event (or find it with events_list + q) and the date (event_dates_list).

  1. Live door. While the show is on, reports_live_attendance lists the dates happening right now with sold, validated and validatedPct (scope: "own" drops hosted shows). Fine to poll, not faster than ~20 s.
  2. Access-close record. event_dates_access_close_status with the date id: live.issued, live.checkins (what a signature would freeze now) and, if already closed, closedCheckins and who signed. Report it; do not sign on your own initiative. event_dates_access_close_sign is irreversible, emails the record to the workspace and needs ADMIN: call it only when the human explicitly asks to sign the record for that date, after showing them the current live.checkins. It opens 2 hours after the start (409 ACCESS_CLOSE_NOT_SIGNABLE_YET gives signableFrom); 409 ACCESS_ALREADY_CLOSED means it is done — do not retry.
  3. Capacity and sold. reports_inventory with eventDateId (groupBy: "ticketType"): capacity, sold, reserved, available.
  4. Revenue. reports_by_event with from/to around the date, and reports_timeseries (interval: "day", event) for the sales curve.
  5. Stuck payments. sales_payment_intents with event and eventDate (onlyAbandoned: true for journeys that picked seats and never paid): funnel gives the drop-off, each journey its stage and outcome (REJECTED carries the gateway reason). For a specific PENDING sale, sales_list with eventDate and status: "PENDING", then sales_attempts explains what the gateway did. Releasing the stock of a PENDING sale whose payment never started is sales_abandon; cancelling or refunding a confirmed one is sales_cancel / sales_refund. All three are irreversible: only on explicit request.
  6. Door, one ticket. tickets_access with its QR code (read-only). Admitting someone is tickets_checkin — only on request.
  7. Attendees. reports_export_attendees with eventDate (one row per ticket). It contains personal data: summarize, do not paste it whole unless asked. The same goes for names and emails in sales_payment_intents.
  8. Money. reports_financials with event (gross, fees, net to settle per date) and settlements_list with event for the payout status. settlements_document returns a 5-minute signed link, not the file.

Close with a short summary: validated / sold / capacity (%), access-close status (open, or signed with the frozen count), gross and net, abandoned or failed payments needing attention, and the settlement status.

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.