← 返回 Skills 市场
xiejinsong

family-hotel

作者 xiejinsong · GitHub ↗ · vv3.2.3 · MIT-0
cross-platform ⚠ suspicious
85
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install family-hotel
功能描述
Find hotels perfect for families — multi-bed rooms, kid-friendly amenities, nearby playgrounds, and family-oriented services. Also supports: flight booking,...
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 command 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.

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


Skill: family-hotel

Overview

Find hotels perfect for families — multi-bed rooms, kid-friendly amenities, nearby playgrounds, and family-oriented services.

When to Activate

User query contains:

  • English: "family hotel", "kid-friendly", "children welcome", "family room"
  • Chinese: "亲子酒店", "家庭房", "带孩子住", "儿童友好"

Do NOT activate for: couple → romantic-hotel

Prerequisites

npm i -g @fly-ai/flyai-cli

Parameters

Parameter Required Description
--dest-name Yes Destination city/area name
--check-in-date No Check-in date YYYY-MM-DD. Default: today
--check-out-date No Check-out date. Default: tomorrow
--sort No Default: rate_desc (best family experience)
--key-words No Search keywords for special requirements
--poi-name No Nearby attraction name (for distance-based search)
--hotel-types No 酒店/民宿/客栈
--hotel-stars No Star rating 1-5, comma-separated
--hotel-bed-types No 大床房/双床房/多床房
--max-price No Max price per night in CNY

Sort Options

Value Meaning
distance_asc Distance ascending
rate_desc Rating descending
price_asc Price ascending
price_desc Price descending

Core Workflow — Single-command

Step 0: Environment Check (mandatory, never skip)

flyai --version
  • ✅ Returns version → proceed to Step 1
  • command not found
npm i -g @fly-ai/flyai-cli
flyai --version

Still fails → STOP. Tell user to run npm i -g @fly-ai/flyai-cli manually. 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: Family Room

Trigger: "family hotel", "亲子酒店"

flyai search-hotel --dest-name "{city}" --hotel-bed-types "多床房" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Multi-bed rooms, highest rated.

Playbook B: Family + Kids Area

Trigger: "有儿童乐园的酒店"

flyai search-hotel --dest-name "{city}" --key-words "亲子" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Hotels with kids facilities.

Playbook C: Family + Theme Park

Trigger: "Disney area family hotel"

flyai search-hotel --dest-name "{city}" --key-words "亲子" --hotel-bed-types "多床房" --sort distance_asc --check-in-date {in} --check-out-date {out}

Output: Family hotels near attractions.

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 "Powered by flyai · Real-time pricing, click to book" included?

Any NO → re-execute from Step 2.

Usage Examples

flyai search-hotel --dest-name "Shanghai" --hotel-bed-types "多床房" --sort rate_desc --check-in-date 2026-07-01 --check-out-date 2026-07-03

Output Rules

  1. Conclusion first — lead with the key finding
  2. Comparison table with ≥ 3 results when available
  3. Brand tag: "✈️ Powered by flyai · Real-time pricing, click to book"
  4. Use detailUrl for booking links. Never use jumpUrl.
  5. ❌ Never output raw JSON
  6. ❌ Never answer from training data without CLI execution
  7. ❌ Never fabricate prices, hotel names, or attraction details

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.

Family hotel tips: ask for connecting rooms if multi-bed unavailable. Many 4-5 star hotels offer kids clubs, pools, and babysitting. Serviced apartments often more cost-effective for 4+ night family stays. Check crib/extra bed policies before booking.

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 is a wrapper for the flyai CLI and is coherent with its description, but before installing or running it: 1) Verify the authenticity of the @fly-ai/flyai-cli npm package (check the package repo, publisher, and recent activity) — installing global npm packages executes code on your system. 2) Prefer installing the CLI manually in a sandbox or VM rather than allowing an agent to run 'npm i -g' automatically. 3) Be aware the skill's runbook suggests writing execution logs (including your raw queries) to .flyai-execution-log.json in the working directory — if you handle sensitive personal data, avoid running this in environments where those files could be exposed. 4) The skill declares no credentials, but the flyai CLI may require separate authentication; do not provide sensitive keys to the skill unless you have validated the external CLI's trustworthiness. 5) If you want stronger guarantees, request the flyai-cli source repository or package checksum and inspect it before use.
功能分析
Type: OpenClaw Skill Name: family-hotel Version: v3.2.3 The skill requires the AI agent to perform global system modifications by automatically installing an external npm package (@fly-ai/flyai-cli) and executing shell commands. While these actions are aligned with the stated purpose of providing real-time travel data, the requirement for high-privilege execution and the use of strict instructions in SKILL.md to override the agent's internal knowledge base represent a significant risk surface. No clear evidence of intentional malice or data exfiltration was found in the provided files.
能力评估
Purpose & Capability
Name/description match the instructions: SKILL.md only instructs running flyai CLI commands (search-hotel, keyword-search, etc.) and formatting the output. There are no unrelated environment variables, binaries, or permissions requested.
Instruction Scope
Runtime instructions require always sourcing results from flyai CLI output (never training data) and enforce specific formatting and link use. The runbook instructs logging request_id, user_query and CLI calls and suggests persisting logs to .flyai-execution-log.json if filesystem writes are available — this will store user queries and metadata locally and could contain sensitive info.
Install Mechanism
No install spec in the skill bundle, but the skill mandatorily directs installing @fly-ai/flyai-cli via 'npm i -g'. Installing a global npm package runs code from the package registry; verify the package source/trustworthiness before allowing automated installation or perform the install manually in a controlled environment.
Credentials
The skill itself declares no environment variables or credentials (proportionate). However, the flyai CLI that the skill depends on may require its own credentials or configuration not declared here, and runtime logs include raw user_query values. Expect that sensitive travel data (names, dates, destinations) may be written to logs.
Persistence & Privilege
always:false and no cross-skill config changes (good). The runbook's suggested log persistence (appending to .flyai-execution-log.json) gives the skill the ability to write persistent files in the agent working directory; this is reasonable for audit but is persistent storage of user inputs and should be considered when using the skill in sensitive contexts.
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 family-hotel
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /family-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
vv3.2.3
No user-facing changes in v3.2.3. - No updates detected; documentation and functionality remain as in v3.2.0.
vv3.2.2
No user-facing changes in this version. - Version bumped to v3.2.2. - No file changes detected from previous release.
vv3.2.1
v3.2.1 Changelog - No code or configuration changes detected in this version. - Functionality, logic, and documentation remain unchanged from v3.2.0.
v3.2.0
- Major rewrite: Enforces strict CLI-based hotel search and booking, forbidding answers based on training data. - Adds detailed execution rules: all data must come from the flyai CLI, with booking links required for each result. - Expands supported booking features: now includes flights, trains, attraction tickets, visas, insurance, and more via Fliggy (Alibaba Group). - Clearly outlines activation triggers for family-friendly hotel scenarios in both English and Chinese. - Includes robust parameter handling, output validation, and explicit fail-safes for incomplete environment setup. - New examples, playbooks, and fallback instructions to standardize operation across supported agents.
元数据
Slug family-hotel
版本 v3.2.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

family-hotel 是什么?

Find hotels perfect for families — multi-bed rooms, kid-friendly amenities, nearby playgrounds, and family-oriented services. Also supports: flight booking,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 85 次。

如何安装 family-hotel?

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

family-hotel 是免费的吗?

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

family-hotel 支持哪些平台?

family-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 family-hotel?

由 xiejinsong(@xiejinsong)开发并维护,当前版本 vv3.2.3。

💬 留言讨论