This project provides an AI agent skill for seamless travel planning and booking directly within conversational AI environments like Claude Code and OpenClaw. It targets users who want to research and arrange flights, hotels, attractions, and other travel services using natural language, eliminating the need to switch between applications or browser tabs. The primary benefit is an integrated, context-aware travel search experience powered by Fliggy's extensive inventory.

How It Works

The FlyAI skill operates by intercepting travel-related natural language queries within compatible AI agents. Upon detection, it invokes the flyai-cli, a Node.js-based command-line interface. This CLI tool then interfaces with the Fliggy MCP API to retrieve structured travel data. The system is designed for a "natural language in, structured data out" paradigm, converting conversational requests into precise, actionable JSON outputs that agents can format for display or further processing.

Quick Start & Requirements

• Installation:
  • OpenClaw: clawhub install flyai or npx skills add alibaba-flyai/flyai-skill.
  • Claude Code: cp -r /path/to/flyai-skill/skills/flyai ~/.claude/skills/flyai.
  • CLI: npm i -g @fly-ai/flyai-cli.
• Prerequisites: Node.js and npm are required for the flyai-cli.
• Configuration: Optional API key for enhanced results via flyai config set FLYAI_API_KEY "your-key".
• Links: Homepage, Quick Start, Commands, and Examples are referenced but not provided as direct URLs.

Highlighted Details

• Four specialized commands: fliggy-fast-search (comprehensive meta-search), search-flight (detailed flight filtering), search-hotels (destination-based hotel search), and search-poi (attraction and activity discovery).
• Supports natural language queries in English and Chinese.
• Covers a wide spectrum of travel categories including transport, accommodation, experiences, events, services (visas, SIMs), and package trips.
• Provides structured, bookable results with direct booking links.
• Designed for zero-configuration setup.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or roadmap are provided in the README.

Licensing & Compatibility

The project is licensed under the MIT License. Copyright is attributed to alibaba-flyai with a stated year of 2026. The MIT license is generally permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

The skill is dependent on specific AI agent frameworks (OpenClaw, Claude Code) and requires the flyai-cli to be installed. The README does not detail specific performance benchmarks, error handling strategies, or known bugs. The copyright year "2026" may indicate a future-dated project or a typographical error.