Show Booking
name: show-booking
by danielfoch · published 2026-03-22
$ claw add gh:danielfoch/danielfoch-show-booking---
name: show-booking
description: Book real estate showing tours from emailed or pasted listing details, including extracting listing data, preparing outbound call jobs, coordinating a calling sub-agent, creating calendar invites, and returning confirmations. Use when the user asks to book showings for one or more properties, coordinate preferred windows for a client, or automate office calls instead of manual BrokerBay login flows.
---
# Show Booking
Overview
Execute an end-to-end workflow for showing requests:
1. Parse intake from free-form prompt or email text.
2. Build per-listing call jobs.
3. Hand off call execution to the `tour-booking` sub-agent.
4. Generate calendar invite files from confirmed slots.
5. Return a concise confirmation summary.
Inputs
Collect these fields before running outbound calls:
If any listing is missing a phone number, flag it as `blocked` and do not place calls for that listing.
Workflow
1) Parse intake
Run:
python3 scripts/intake_request.py --input-file /path/to/intake.txt --output /tmp/showing-intake.jsonOr pass inline text:
python3 scripts/intake_request.py --input-text "Book showings for ..." --output /tmp/showing-intake.json2) Build call queue
Run:
python3 scripts/orchestrate_showings.py --intake /tmp/showing-intake.json --output /tmp/showing-plan.jsonThis produces:
3) Delegate calling to `tour-booking`
For each `call_queue` record, invoke `tour-booking/scripts/place_outbound_call.py` with:
If live calling is not approved, run with `--dry-run` and return the generated payload.
4) Create invites for confirmed slots
When a listing returns a confirmed date/time:
python3 scripts/create_invite_ics.py \
--input /tmp/confirmed-showings.json \
--output-dir /tmp/showing-invitesThe script emits one `.ics` file per confirmed showing. Import into Google Calendar or send directly as attachments.
5) Return status
Report:
Guardrails
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...