tc-deeptrip: AI Travel Assistant for Openclaw

An AI-powered travel assistant integrated with Tongcheng Travel for hotel search, transportation booking, and itinerary planning.

tclxhai-lv
v1.0.4
Apr 12, 2026
1
986
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install tc-deeptrip

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install tc-deeptrip using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is tc-deeptrip: AI Travel Assistant?

tc-deeptrip is a comprehensive travel service skill powered by Tongcheng Travel's large language model and integrated into the Openclaw Skills ecosystem. It enables AI agents to provide expert-level travel recommendations, including real-time hotel availability, flight and high-speed rail options, and curated local attractions. By bridging the gap between natural language queries and structured travel data, this tool allows users to plan entire trips and access direct booking links for both mobile and PC platforms through Openclaw Skills.

tc-deeptrip: AI Travel Assistant Use Cases

  • Searching for hotels near specific landmarks with customized price and star-rating filters
  • Comparing flight and high-speed rail options between cities for optimal travel timing
  • Generating multi-day travel itineraries for major tourist destinations like Chengdu or Beijing
  • Obtaining direct booking links for travel products to complete reservations instantly

How tc-deeptrip: AI Travel Assistant Works

  1. The user submits a travel-related request to the agent using the Openclaw Skills framework.
  2. The agent enriches the query with necessary context like departure location and dates to ensure a precise API response.
  3. The query.py script sends a structured POST request to the deeptrip-claw API gateway.
  4. The system processes the intent through the Tongcheng Travel LLM to find the best matching products and routes.
  5. The Openclaw Skills agent returns a formatted response featuring descriptive text and deep-links for mobile and desktop booking.

tc-deeptrip: AI Travel Assistant Setup

To get started with this skill, follow these installation and configuration steps:

  1. Ensure you have the Python environment ready within your agent directory.
  2. (Optional) Obtain an API Key from the Tongcheng Travel AI sharing page or via the Tongcheng App.
  3. Configure the API Key for persistent use:
python scripts/query.py --config your-api-key
  1. For the best booking experience, use the provided QR link in the documentation to log in to your Tongcheng Travel account via WeChat.

tc-deeptrip: AI Travel Assistant Data Schema & Taxonomy

The skill manages data through a structured internal taxonomy and configuration files:

Component Type Description
config.json File Stores persistent API keys and environment settings
code String Status code where 0 indicates success and specific errors handle rate limits
data.text String Markdown-formatted AI response with travel recommendations
data.links Object Dictionary containing PC and Mobile URLs for specific travel products
_meta.json File Metadata defining the Openclaw Skills identifier and author info

tc-deeptrip: AI Travel Assistant Advanced Features

  • Context Enrichment: Supports manual context injection to handle multi-turn dialogue simulation despite the stateless API
  • Dual-Platform Deep Linking: Generates separate URLs optimized for desktop browsers and mobile app environments
  • Persistent Configuration: CLI tools for managing API keys and clearing local configurations
  • Rate Limit Management: Error handling for IP limits with guided instructions for obtaining higher-tier API access through Openclaw Skills

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*