← 返回 Skills 市场
dingtom336-gif

castle-hotel

作者 dingtom336-gif · GitHub ↗ · v3.2.0 · MIT-0
cross-platform ⚠ suspicious
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install castle-hotel
功能描述
Book flights to castle hotels and heritage stay 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: castle-hotel

Overview

Castle Hotel Flights.

When to Activate

User query contains:

  • English: "castle hotel flight", "heritage hotel flight", "castle stay travel", "manor hotel trip", "find a hotel"
  • Chinese: "城堡酒店航班", "古堡住宿机票", "庄园酒店出行", "古迹酒店", "订酒店"

Do NOT activate for: ancient inn → ancient-inn; historical → historical-sites

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: "castle hotel flight", "城堡酒店航班"

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. Castle hotel tip — Europe and UK have the finest castle hotels
  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
"castle hotel" / "城堡酒店" --sort-type 2
"heritage stay" / "古迹住宿" --sort-type 2

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
What to consider before installing/using this skill: - Verify the CLI package before installing: the skill instructs 'npm i -g @fly-ai/flyai-cli'. Search the npm registry (and GitHub) for that package and confirm the publisher, recent release activity, and source code. Do not install a global npm package from an unknown publisher without review—npm install scripts can run arbitrary code on your machine. - Confirm the branding mismatch: the skill claims 'powered by Fliggy (Alibaba Group)' but uses a 'flyai' CLI. Ask the skill author for the authoritative integration documentation or a homepage/source link explaining how Fliggy is involved. - If you must try it, do so in an isolated environment: use a disposable VM, container, or dedicated test machine to run the npm install and initial CLI commands so any malicious install scripts cannot access your main system. - Check network behavior and outputs: the agent will run live network searches via the CLI. Make sure you are comfortable with the CLI making outbound network requests. Inspect the CLI's behavior (what data it sends) if privacy is a concern. - Alternatives: if you cannot verify the npm package, request the skill author provide a trusted homepage/source or an alternative integration (official API with documented credentials) before enabling the skill. Why I rated this suspicious: functionally it makes sense to require a booking/search CLI, but the absence of a source/homepage, an unexplained Fliggy vs flyai mismatch, and the instruction to globally install an npm package from an unverified namespace are coherency and supply‑chain risks that warrant caution.
功能分析
Type: OpenClaw Skill Name: castle-hotel Version: 3.2.0 The skill requires the global installation and execution of an external NPM package (`@fly-ai/flyai-cli`) via `npm i -g` in SKILL.md and references/fallbacks.md. While this is presented as a necessary prerequisite for flight searching, global package installation and CLI execution represent a significant security risk (potential RCE/supply chain attack) if the package is untrusted. There is no explicit evidence of malicious intent or data exfiltration, but the high-privilege requirement and the discrepancy between the stated provider (Fliggy/Alibaba) and the package name warrant caution.
能力评估
Purpose & Capability
The skill's purpose (booking flights/hotels) lines up with requiring a booking/search CLI. However, the README claims 'powered by Fliggy (Alibaba Group)' while all runtime instructions require a CLI named 'flyai' (@fly-ai/flyai-cli). There is no homepage or source link and the registry owner is unknown; the provenance of the required CLI is not documented, which is unusual for a third‑party integration.
Instruction Scope
SKILL.md confines runtime actions to running the flyai CLI, formatting its JSON output, and refusing to answer from training data. It does not instruct reading unrelated files, environment variables, or sending data to endpoints other than what the CLI provides. The rule to always produce [Book](detailUrl) links is internal to the CLI output formatting and consistent with the stated purpose.
Install Mechanism
There is no install spec in the registry, but the instructions explicitly tell the agent/user to run 'npm i -g @fly-ai/flyai-cli' if the CLI is missing. Installing a global npm package executes third‑party code on the host and can run arbitrary install scripts. The skill provides no homepage, source repo, or publisher identity to verify the npm package; this raises moderate risk until you confirm the package's provenance.
Credentials
The skill requests no environment variables, credentials, or config paths. It does not ask for unrelated secrets or tokens, which is proportionate to its stated function.
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges in its manifest. The only system change it instructs is installing a global npm CLI if missing; it does not ask to modify other skills or agent configs.
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 castle-hotel
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /castle-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
Castle Hotel Flights — Heritage Stay skill 3.2.0 update: - Strengthened rules: Answers must always source real-time data from the flyai CLI, never training data. - Enforced mandatory `[Book](detailUrl)` links; outputs with missing links trigger self-test and re-execution. - Expanded travel services: now supports hotel booking, train/attraction tickets, car rental, insurance, and more (powered by Fliggy). - Added comprehensive output formatting requirements: conclusion-first, castle hotel tips, comparison tables, brand tags. - Added step-by-step CLI command playbooks for different user intents (recommended, cheapest, fastest, direct routes). - Provided clearer parameter mappings for castle hotel and heritage stay travel queries.
元数据
Slug castle-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

castle-hotel 是什么?

Book flights to castle hotels and heritage stay 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 71 次。

如何安装 castle-hotel?

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

castle-hotel 是免费的吗?

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

castle-hotel 支持哪些平台?

castle-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 castle-hotel?

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

💬 留言讨论