OpenClaw

tour-booking

Sub-agent for outbound listing-office calls to request and confirm property showing slots using a provided call script and structured payloads. Use when a parent workflow needs call execution for one or more listings, including dry-run payload generation, live ElevenLabs call requests, and parsing call outcomes into booking statuses.

danielfoch0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install danielfoch/tour-booking

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Tour Booking

Overview

Handle the call execution layer for property showing bookings:

Build a consistent call prompt from listing and client data.
Send outbound call request to ElevenLabs (or dry-run).
Normalize call outcome into structured status fields.

Inputs

Each call job should include:

job_id
client_name
listing.address
listing.office_phone
preferred_windows_text
timezone

Runbook

1) Build payload

python3 scripts/prepare_call_payload.py \
  --job /tmp/job.json \
  --output /tmp/call-payload.json

2) Place call

Dry-run (default safe mode):

python3 scripts/place_outbound_call.py \
  --payload /tmp/call-payload.json \
  --output /tmp/call-result.json \
  --dry-run

Live mode:

python3 scripts/place_outbound_call.py \
  --payload /tmp/call-payload.json \
  --output /tmp/call-result.json \
  --live

3) Parse outcome

python3 scripts/parse_call_result.py \
  --input /tmp/call-result.json \
  --output /tmp/booking-outcome.json

Call Guardrails

State clearly that the caller is an AI assistant calling on behalf of the realtor.
Ask for available slots inside the requested window first; request alternatives if unavailable.
Confirm final slot with exact date and local time before ending the call.
If the office cannot confirm, mark as pending_callback and capture callback requirements.

来源信息

Source: github
Repository: openclaw/skills
Path: skills/danielfoch/tour-booking
Version: —
Commit: 674d1442f5cfda40ad76573b77ea6bb0216e631e
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Tour Booking

## Overview

Handle the call execution layer for property showing bookings:
1. Build a consistent call prompt from listing and client data.
2. Send outbound call request to ElevenLabs (or dry-run).
3. Normalize call outcome into structured status fields.

## Inputs

Each call job should include:
- `job_id`
- `client_name`
- `listing.address`
- `listing.office_phone`
- `preferred_windows_text`
- `timezone`

## Runbook

### 1) Build payload

```bash
python3 scripts/prepare_call_payload.py \
  --job /tmp/job.json \
  --output /tmp/call-payload.json
```

### 2) Place call

Dry-run (default safe mode):

```bash
python3 scripts/place_outbound_call.py \
  --payload /tmp/call-payload.json \
  --output /tmp/call-result.json \
  --dry-run
```

Live mode:

```bash
python3 scripts/place_outbound_call.py \
  --payload /tmp/call-payload.json \
  --output /tmp/call-result.json \
  --live
```

### 3) Parse outcome

```bash
python3 scripts/parse_call_result.py \
  --input /tmp/call-result.json \
  --output /tmp/booking-outcome.json
```

## Call Guardrails

- State clearly that the caller is an AI assistant calling on behalf of the realtor.
- Ask for available slots inside the requested window first; request alternatives if unavailable.
- Confirm final slot with exact date and local time before ending the call.
- If the office cannot confirm, mark as `pending_callback` and capture callback requirements.

搜索