← 返回 Skills 市场
xiejinsong

holiday-flights

作者 xiejinsong · GitHub ↗ · vv3.2.1 · MIT-0
cross-platform ⚠ suspicious
81
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install holiday-flights
功能描述
Find flights during Chinese peak travel seasons — Spring Festival, Golden Week, Labor Day, Dragon Boat. Warns about high demand and suggests optimal 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: holiday-flights

Overview

Find flights during Chinese peak travel seasons — Spring Festival, Golden Week, Labor Day, Dragon Boat. Warns about high demand and suggests optimal booking windows.

When to Activate

User query contains:

  • English: "Spring Festival", "Golden Week", "holiday flight", "Chinese New Year", "Labor Day"
  • Chinese: "春节机票", "国庆机票", "假期飞", "五一机票", "端午机票"

Do NOT activate for: regular dates → cheap-flights

Prerequisites

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

Parameters

Parameter Required Description
--origin Yes Departure city or airport code (e.g., "Beijing", "PVG")
--destination Yes Arrival city or airport code (e.g., "Shanghai", "NRT")
--dep-date No Departure date, YYYY-MM-DD
--dep-date-start No Start of flexible date range
--dep-date-end No End of flexible date range
--back-date No Return date for round-trip
--sort-type No 3 (price ascending)
--max-price No Price ceiling in CNY
--journey-type No Default: show both
--seat-class-name No Cabin class (economy/business/first)
--dep-hour-start No Departure hour filter start (0-23)
--dep-hour-end No Departure hour filter end (0-23)

Sort Options

Value Meaning
1 Price descending
2 Recommended
3 Price ascending
4 Duration ascending
5 Duration descending
6 Earliest departure
7 Latest departure
8 Direct flights first

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: Spring Festival

Trigger: "春节回家", "CNY flight"

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

Output: Warn: prices 50-200% higher. Book 1-2 months ahead.

Playbook B: Golden Week

Trigger: "国庆出游"

flyai search-flight --origin "{o}" --destination "{d}" --dep-date-start 2026-09-28 --dep-date-end 2026-10-03 --sort-type 3

Output: Suggest departing 1-2 days early to save 30-50%.

Playbook C: Labor Day / Dragon Boat

Trigger: "五一/端午"

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

Output: 3-day mini-holidays. Book 2-3 weeks ahead.

Playbook D: Anti-Peak Strategy

Trigger: "避开高峰"

flyai search-flight --origin "{o}" --destination "{d}" --dep-date {holiday_start+2} --sort-type 3

Output: Search offset dates — depart 2 days after holiday starts for 40-60% savings.

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-flight --origin "Guangzhou" --destination "Chengdu" --dep-date 2026-10-01 --sort-type 3

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.

Chinese peak seasons and typical price multipliers: Spring Festival (Jan/Feb) 2-3x, Qingming (Apr) 1.5x, Labor Day (May) 1.5x, Dragon Boat (Jun) 1.3x, Summer (Jul-Aug) 1.3x, Mid-Autumn (Sep) 1.3x, Golden Week (Oct) 2-3x. Optimal booking: 1-2 months for Spring Festival/Golden Week, 2-3 weeks for minor holidays.

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 says (wraps a flyai CLI) but has a few red flags you should consider before installing or running it: 1) Metadata omits the required CLI; SKILL.md requires installing @fly-ai/flyai-cli globally at runtime — verify the package's source (npm page, repo, maintainers) before installing. 2) The runbook tells the agent to persist detailed execution logs (.flyai-execution-log.json) which may contain user queries or PII; decide whether you want those written to disk. 3) SKILL.md/fallbacks suggest using 'sudo npm i -g' if install fails — avoid running sudo installs unless you trust and have reviewed the package. 4) Prefer to install and vet the flyai CLI yourself (in a sandbox or VM), run searches locally, and provide sanitized outputs to the agent rather than allowing the agent to install packages or write persistent logs. 5) Ask the publisher for a homepage/repository link or the CLI source code so you can audit the package and confirm the 'Powered by flyai' claim. If you cannot verify the CLI package or you want to avoid persistent logs/global installs, treat this skill as risky.
功能分析
Type: OpenClaw Skill Name: holiday-flights Version: v3.2.1 The skill mandates the global installation of an external NPM package (`@fly-ai/flyai-cli`) and explicitly suggests using `sudo` in its fallback logic (`references/fallbacks.md`) to ensure the `flyai` CLI is available. While these actions are functionally aligned with the flight-search purpose, they represent high-risk system modifications (RCE and privilege escalation) within the agent's environment. The `SKILL.md` also employs aggressive instructions to prevent the agent from using its own knowledge, forcing reliance on the external binary.
能力评估
Purpose & Capability
Skill name/description (holiday-flights using flyai) align with using a vendor CLI, but registry metadata declares no required binaries or install steps while SKILL.md mandates installing and using @fly-ai/flyai-cli. That mismatch (metadata says 'none' but runtime requires a CLI) is an inconsistency. README references a parent flyai skill and a GitHub path, but the 'Source' and 'Homepage' fields are unknown/missing in the registry, reducing traceability.
Instruction Scope
SKILL.md tightly constrains the agent to obtain all data from the flyai CLI and to never use training data. The runbook instructs the agent to create and persist an execution log (.flyai-execution-log.json) containing user_query and CLI results. Persisting these logs could capture sensitive user input or PII. The docs also instruct fallbacks that include running privileged installs (suggesting 'sudo npm i -g' in fallback guidance).
Install Mechanism
There is no formal install spec in the registry, but SKILL.md instructs runtime installation via 'npm i -g @fly-ai/flyai-cli' (and suggests 'sudo' if needed). Global npm installs can execute package install scripts and modify the system; asking an agent to perform this at runtime (and suggesting sudo) is a moderate-to-high risk and should be explicitly declared in metadata and reviewed before running.
Credentials
The skill requests no environment variables or credentials, which is appropriate for a search/booking helper. However, because the skill's runbook logs CLI commands, requests, and results, those logs could contain sensitive details (dates, passenger names, queries). That implicit access to potentially sensitive data is not declared in requires.env.
Persistence & Privilege
The runbook explicitly directs creating persistent logs (.flyai-execution-log.json) if filesystem writes are available, introducing persistent storage of user queries and CLI outputs. Combined with runtime instructions to install a global npm package (potentially with sudo), this grants the skill the ability to persist data and change the host environment — a privilege that should be made explicit and limited.
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 holiday-flights
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /holiday-flights 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
vv3.2.1
No user-facing changes in this release; version number updated only.
v3.2.0
**Major update: Strict execution and output framework; expanded coverage.** - Enforces CLI execution only—never answers from model data; all responses sourced from flyai CLI output. - Detailed critical execution rules and environment checks, including mandatory CLI installation handling. - Expanded support for hotels, train tickets, attractions, visas, insurance, and car rental via Fliggy. - Precise parameter mapping and multi-scenario holiday playbooks for peak Chinese holidays. - Standardizes output: booking links required, user language respected, markdown tables, and branding. - Updated compatibility information for a broader range of agents.
元数据
Slug holiday-flights
版本 v3.2.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

holiday-flights 是什么?

Find flights during Chinese peak travel seasons — Spring Festival, Golden Week, Labor Day, Dragon Boat. Warns about high demand and suggests optimal booking... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 81 次。

如何安装 holiday-flights?

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

holiday-flights 是免费的吗?

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

holiday-flights 支持哪些平台?

holiday-flights 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 holiday-flights?

由 xiejinsong(@xiejinsong)开发并维护,当前版本 vv3.2.1。

💬 留言讨论