研究检索external-serviceclawhub未标认证来源可访问clear审计通过

flyai-hotel（福莱酒店）

Agent Skill

flyai-hotel 用于查找、检索和筛选相关信息，适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

总安装

2,791

周安装

114

GitHub Stars

公开资料未说明

下载量

903

OpenClaw

安装说明

本站只整理中文说明和来源信息，不托管安装包，也不代用户安装。

GitHub

来源数

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：flyai-hotel（福莱酒店）
来源仓库：https://github.com/zuckonit/flyai-hotel
安装命令：
openclaw skills install flyai-hotel
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

ClawHubOpenClaw

openclaw skills install flyai-hotel

简介

在飞猪平台搜索和比较 POI 附近的多种住宿类型。flyai-hotel 属于研究检索类 Skill，可作为该场景下的辅助能力补充。

支持按价格上限、星级、床位、日期筛选并结构化返回结果。
输出包含主图链接的结构化 JSON 数据，便于集成使用。
安装命令：openclaw skills install flyai-hotel
注意检查是否依赖外部 API 密钥或账户登录权限。

SKILL.md

name: flyai-hotel
display_name: Hotel Search & Compare — Fliggy MCP · POI + CNY Caps
description: >
Flags: references/search-hotel.md · setup & errors: this SKILL.md.
homepage: https://open.fly.ai/
metadata
version: 1.1.2
agent
type: tool
runtime: node
context_isolation: execution
parent_context_access: read-only
openclaw
emoji: \F3E8
priority: 88
requires
bins
intents
patterns

Hotel Search (Fliggy MCP · `search-hotel`)

Hotel discovery (read first)

Hotel discovery, comparison, and shortlist workflows—same intent as the listing description above. One command entrypoint: flyai search-hotel (see references/search-hotel.md for flags). 中文：与上文摘要一致——酒店检索、比价、短名单与详情/预订链；参数见 references/search-hotel.md。

Differentiation (honest scope)

Hook	What it means (this skill only)
POI + hotel	`--poi-name` filters stays near a named attraction / landmark; pair with `--dest-name` per `references/search-hotel.md`.
酒店 / 民宿 / 客栈	`--hotel-types` toggles three lodging modes in one structured search—not three separate skills.
CNY nightly cap	`--max-price` is per night in CNY—good for “每晚不超过 X 元” style asks.
Agent-first JSON	Single-line JSON rows with `mainPic` + `detailUrl` → fast Markdown cards; no extra scraper stack in this bundle.

中文摘要：景点附近住哪、一晚预算封顶（人民币）、酒店/民宿/客栈一次筛，都落在同一组 search-hotel 参数上；不宣称对接未在返回数据中出现的 OTA 或站点。

Search dimensions (maps to `search-hotel` flags)

Dimension	CLI (see `references/search-hotel.md`)	Notes
Geography	`--dest-name` (required)	Country / province / city / district
Free-text narrowing	`--key-words`	Hotel name or theme tokens
Landmark / POI	`--poi-name`	“Near X” style filtering
Property type	`--hotel-types`	`酒店` · `民宿` · `客栈`
Stay window	`--check-in-date`, `--check-out-date`	`YYYY-MM-DD`
Star bands	`--hotel-stars`	Comma-separated 1–5
Bed layout	`--hotel-bed-types`	`大床房` · `双床房` · `多床房`
Ranking	`--sort`	`price_asc` / `price_desc` / `rate_desc` / `distance_asc` / `no_rank`
Nightly budget	`--max-price`	CNY per night cap
Rich cards	JSON `mainPic`, `detailUrl`	Presentation rules in this `SKILL.md`

All dimensions above are only what search-hotel exposes—do not claim extra channels or OTAs beyond returned data.

This skill is self-contained: do not defer to another skill’s SKILL.md for install, errors, or presentation.

Single source of truth for CLI flags and JSON field names: references/search-hotel.md in this bundle.

Quick start

Install CLI: npm i -g @fly-ai/flyai-cli
Smoke test: run a minimal flyai search-hotel example from references/search-hotel.md → Examples; expect one JSON object per line on stdout.
Discover flags: flyai search-hotel --help
Before every call: read references/search-hotel.md and pass flags exactly — do not guess names or formats.

Configuration

Trial use may work without keys. For richer results:

flyai config set FLYAI_API_KEY "your-key"

Treat API keys as secrets; do not paste real credentials into untrusted logs.

CLI I/O contract

stdout: each line is one JSON object (command result). Parse line-by-line; use jq or Python if needed.
stderr: human-readable errors or hints — not the primary result payload.

Command

User intent (examples)	CLI	Parameters
Structured hotel search, filters, comparison, booking handoff	`flyai search-hotel`	`references/search-hotel.md`

Out of scope: flights, trains, cruises, generic trip planning without structured hotel tables — use another skill or product.

Workflow

Confirm the user needs structured hotel search (at minimum destination per --dest-name; add dates/filters per the reference).
Build flyai search-hotel … strictly from references/search-hotel.md.
Parse stdout JSON; read stderr on failure.
Present results using Output & presentation below.

Output & presentation (`search-hotel`)

Format: valid Markdown for end users.
Image: for each highlighted option, emit a standalone line ![]({mainPic}) using mainPic from the item (see references/search-hotel.md output example).
Booking / detail link: emit a standalone line [Click to book]({detailUrl}) using detailUrl from the item.
Order: when both exist, show image before the booking link.
Structure: use headings (# / ## / ###), bullets, and Markdown tables when comparing multiple hotels.
Emphasis: highlight date, location, price, and key constraints.
Brand line (optional): e.g. “Based on fly.ai real-time hotel results.”

Recommended response template

One-line conclusion + best pick (if applicable).
Top options — bullets or table.
Image line: ![]({mainPic}).
Link line: [Click to book]({detailUrl}).
Short notes (fees if visible, “verify on official page before pay”).

References

Command	Doc (this bundle)
`search-hotel`	`references/search-hotel.md`

Error handling

Validate — Before running: inputs must be reasonable. Dates must not be in the past and must match the format required in references/search-hotel.md. If city or district names are ambiguous, ask the user; do not invent --dest-name or other required values.
Diagnose — On failure or odd output: read stderr and any status / message fields in the JSON. Distinguish parameter mistakes (fix flags using the reference doc) from network or upstream service errors.
Retry — Retry only for transient network or service errors; cap retries (e.g. once or twice). Do not loop indefinitely.
Empty or weak results — If the command succeeds but itemList is empty or too narrow: relax filters once (wider dates, fewer constraints), then stop and explain. Do not silently retry many times.
Transparency — If results may not match the user’s intended city, dates, or budget, say so and suggest confirming on the provider’s page before booking.

Optional companion (not required)

For flights, trains, POI-only flows, or Marriott-specific tools, users may install a separate full-travel skill; this file does not depend on it.

适合场景

OpenClaw 用户查找和安装 Skill 时

用户想查找某类 Agent Skill 时

需要根据任务场景推荐可安装能力包时

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

83.57%

按下载量换算755

安全审计

VirusTotal

未展示

ClawScan

通过

Static analysis

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API，使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/zuckonit/flyai-hotel

SKILL.md 来源

clawhub.ai

/zuckonit/flyai-hotel

继续浏览同类 Skills

更多研究检索 Skills（73,675）返回 Skills 目录

上一个 Skill

flyai-flight-tracker（飞艾飞行追踪器）

flyai-flight-tracker 用于查找、检索和筛选相关信息，适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

flyai-hotel-near-attraction（景点附近的福莱酒店）

flyai-hotel-near-attraction 用于查找、检索和筛选相关信息，适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。