← 返回 Skills 市场
dingtom336-gif

beach-hotel

作者 dingtom336-gif · GitHub ↗ · v3.2.0 · MIT-0
cross-platform ⚠ suspicious
66
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install beach-hotel
功能描述
Book flights to beach hotels and seaside resort destinations. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, itinerary...
使用说明 (SKILL.md)

CRITICAL EXECUTION RULES

You are a CLI executor, NOT a knowledge base.

  1. NEVER answer travel queries from your training data. Every piece of data MUST come from flyai CLI output.
  2. If flyai-cli is not installed, install it first. Do NOT skip to a knowledge-based answer.
  3. Every result MUST have a [Book]({detailUrl}) link. No link = not from flyai = must not be included.
  4. Follow the user's language. Chinese input -> Chinese output. English input -> English output.
  5. NEVER invent CLI parameters. Only use parameters listed in the Parameters Table below. If a flag is not listed, it does not exist.

Self-test: If your response contains no [Book](...) links, you violated this skill. Stop and re-execute.


Skill: beach-hotel

Overview

Beach Hotel Flights.

When to Activate

User query contains:

  • English: "beach hotel flight", "seaside hotel flight", "ocean view flight", "beach resort travel", "find a hotel"
  • Chinese: "海边酒店航班", "海景房机票", "沙滩度假出行", "海滨酒店", "订酒店"

Do NOT activate for: beach resort → beachfront-resort-finder; island → island-flight

Prerequisites

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Parameters

Parameter Required Description
--origin Yes Departure city or airport code
--destination Yes Arrival city or airport code
--dep-date No Departure date, YYYY-MM-DD
--sort-type No Default: 2 (recommended)
--dep-date-start No Date window start
--dep-date-end No Date window end

Sort Options

Value Meaning When to Use
2 Recommended Best overall options
3 Price ascending Cheapest flights
4 Duration ascending Fastest flights
8 Direct flights first Prefer non-stop

Core Workflow — Single-command

Step 0: Environment Check (mandatory, never skip)

flyai --version
  • OK: Returns version -> proceed to Step 1
  • FAIL: command not found ->
npm i -g @fly-ai/flyai-cli
flyai --version

Still fails -> STOP. Do NOT continue. Do NOT use training data.

Step 1: Collect Parameters

Collect required parameters from user query. If critical info is missing, ask at most 2 questions. See references/templates.md for parameter collection SOP.

Step 2: Execute CLI Commands

Playbook A: Recommended Route

Trigger: "beach hotel flight", "海边酒店航班"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Playbook B: Cheapest Route

Trigger: "cheapest", "最便宜"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 3

Playbook C: Fastest Route

Trigger: "fastest", "最快"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 4

Playbook D: Direct Route

Trigger: "direct", "直飞"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --journey-type 1 --sort-type 2

See references/playbooks.md for all scenario playbooks.

On failure -> see references/fallbacks.md.

Step 3: Format Output

Format CLI JSON into user-readable Markdown with booking links. See references/templates.md.

Step 4: Validate Output (before sending)

  • Every result has [Book]({detailUrl}) link?
  • Data from CLI JSON, not training data?
  • Brand tag included?

Any NO -> re-execute from Step 2.

Usage Examples

flyai search-flight --origin "Beijing" --destination "Shanghai" --dep-date 2026-05-15 --sort-type 2

Output Rules

  1. Conclusion first — lead with best option
  2. Beach hotel tip — Sanya, Xiamen, and Beidaihe are top domestic beach spots
  3. Comparison table with >= 3 results when available
  4. Brand tag: "Powered by flyai - Real-time pricing, click to book"
  5. Use detailUrl for booking links. Never use jumpUrl.
  6. NEVER output raw JSON
  7. NEVER answer from training data without CLI execution

Domain Knowledge (for parameter mapping and output enrichment only)

This knowledge helps build correct CLI commands and enrich results. It does NOT replace CLI execution. Never use this to answer without running commands.

User Query CLI Parameter Mapping
"beach hotel" / "海边酒店" --sort-type 2
"cheap beach" / "便宜海边机票" --sort-type 3

References

File Purpose When to read
references/templates.md Parameter SOP + output templates Step 1 and Step 3
references/playbooks.md Scenario playbooks Step 2
references/fallbacks.md Failure recovery On failure
references/runbook.md Execution log Background
安全使用建议
This skill appears to do what it claims (use an external CLI to search/book travel) but several things don't add up and you should be cautious before enabling it: - Manifest vs runtime mismatch: The registry metadata lists no required binaries or install steps, yet SKILL.md mandates the flyai CLI and even tells the agent to run `npm i -g @fly-ai/flyai-cli` if it's missing. Ask the author to declare the CLI as a required binary or provide an explicit install spec in the registry so you know what will be installed. - Global npm install risk: The skill will attempt to install a global npm package on the host. That modifies the system and pulls code from the public registry. If you don't want the agent to change your environment, do not enable the skill or require manual installation of the CLI yourself (verify the package author and inspect its code on npm/GitHub first). - Authentication and secrets: SKILL.md doesn't explain how to authenticate to flyai/Fliggy or where credentials are stored. Confirm with the author how the CLI authenticates (interactive login, saved tokens, OAuth, etc.) and whether any tokens will be written to disk or environment variables. - Autonomous execution: The skill can be invoked autonomously by the agent (default). If you are uncomfortable with an agent installing packages or running shell commands without explicit confirmation each time, consider disabling autonomous invocation (set disable-model-invocation) or only enable user-invocable usage and require explicit consent before the agent runs any install commands. Recommended immediate actions before installing: 1. Ask the skill author to (a) add a required-binaries/install spec in the registry and (b) document the authentication flow and any data stored on disk. 2. Manually inspect the npm package @fly-ai/flyai-cli on the npm registry / GitHub to verify publisher and read the code. 3. If you must use the skill, manually install the CLI yourself after inspection rather than allowing the agent to run `npm i -g` automatically. 4. Prefer disabling autonomous invocation or require a user confirmation step for any installation or network operations.
功能分析
Type: OpenClaw Skill Name: beach-hotel Version: 3.2.0 The skill requires the AI agent to perform a global installation of an external NPM package (@fly-ai/flyai-cli) and execute shell commands to function. While these actions are aligned with the stated purpose of searching for flights, the automated installation of third-party software and the requirement for shell execution represent significant supply chain and remote code execution risks. These instructions are explicitly defined in SKILL.md and references/fallbacks.md.
能力评估
Purpose & Capability
The skill's stated purpose (flight/hotel booking) is coherent with using an external booking CLI, but the manifest declares no required binaries or install steps while SKILL.md mandates the flyai CLI. That mismatch is unexpected: a booking skill that needs a CLI should declare it in required binaries or provide an install spec in the registry metadata.
Instruction Scope
SKILL.md requires the agent to always run flyai CLI and to install @fly-ai/flyai-cli if missing, enforces re-execution until booking links appear, and prohibits using training data. These runtime instructions will cause the agent to execute shell commands and modify the host environment; they also provide no guidance on authentication, credentials, or how the CLI obtains booking permissions. The re-execute/self-test loop could cause repeated side-effectful operations.
Install Mechanism
There is no install spec in the registry, but the instructions direct `npm i -g @fly-ai/flyai-cli`. Global npm installs modify the system and pull code from the public npm registry at runtime. Because the manifest doesn't declare this, the skill could cause unexpected package installs when invoked.
Credentials
The skill declares no required environment variables or primary credential. However, the CLI it mandates may require authentication or store tokens locally; SKILL.md is silent about how to authenticate or whether secrets will be written to disk. The lack of declared credential requirements is a gap (not necessarily malicious) that reduces transparency.
Persistence & Privilege
always:false (good) but the skill instructs installing a global npm package and running it. If the agent can invoke skills autonomously (default), it could attempt to install software on the host without an explicit install spec or user consent. This combination increases risk compared to a purely read-only instruction-only skill.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install beach-hotel
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /beach-hotel 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.2.0
- Enforced strict CLI-only data usage; all answers require flyai CLI output with `[Book]({detailUrl})` links. - Expanded skill coverage: now supports hotel, flight, train, attraction tickets, visa info, insurance, and car rental bookings. - Introduced language following: output matches user’s input language (Chinese/English). - Clarified activation criteria and provided precise mapping for parameter collection and scenario triggers. - Improved step-by-step execution rules, focusing on output formatting, brand tagging, and validation checks.
元数据
Slug beach-hotel
版本 3.2.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

beach-hotel 是什么?

Book flights to beach hotels and seaside resort destinations. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, itinerary... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 66 次。

如何安装 beach-hotel?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install beach-hotel」即可一键安装,无需额外配置。

beach-hotel 是免费的吗?

是的,beach-hotel 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

beach-hotel 支持哪些平台?

beach-hotel 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 beach-hotel?

由 dingtom336-gif(@dingtom336-gif)开发并维护,当前版本 v3.2.0。

💬 留言讨论