← 返回 Skills 市场
xiejinsong

first-class

作者 xiejinsong · GitHub ↗ · v3.2.0 · MIT-0
cross-platform ⚠ suspicious
72
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install first-class
功能描述
Book first class flights, premium cabin tickets and luxury airline seats with lie-flat beds and lounge access. Also supports: flight booking, hotel reservati...
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: first-class

Overview

Book first class flights — premium cabins with lie-flat seats, priority boarding, and airport lounge access. For travelers who value comfort and exclusivity over price.

When to Activate

User query contains:

  • English: "first class", "premium cabin", "lie-flat seat", "luxury flight", "VIP flight", "top tier cabin"
  • Chinese: "头等舱", "豪华舱", "VIP机票", "最高舱位", "平躺座位", "贵宾航班"

Do NOT activate for: business class → business-flights

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 (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
--sort-type No Default: 2 (recommended)
--max-price No Price ceiling in CNY
--journey-type No 1=direct, 2=connecting
--seat-class-name No Always first for this skill
--dep-hour-start No Departure hour filter start (0-23)
--dep-hour-end No Departure hour filter end (0-23)

Sort Options

Value Meaning When to Use
2 Recommended Default — best first class options
3 Price ascending Compare first class pricing
4 Duration ascending Fastest premium route
8 Direct flights first Non-stop first class only

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: Recommended First Class

Trigger: "first class flights", "头等舱机票"

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

Output: Best first class options sorted by recommendation.

Playbook B: Cheapest First Class

Trigger: "cheapest first class", "最便宜的头等舱"

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

Output: First class flights sorted by lowest price.

Playbook C: Direct First Class Only

Trigger: "direct first class", "直飞头等舱"

flyai search-flight --origin "{o}" --destination "{d}" --dep-date {date} --seat-class-name first --journey-type 1 --sort-type 4

Output: Non-stop first class flights, fastest duration first.

Playbook D: Broad Search (no first class found)

Trigger: fallback when 0 results

flyai search-flight --origin "{o}" --destination "{d}" --dep-date {date} --seat-class-name first --sort-type 2
flyai keyword-search --query "{origin} to {destination} first class flights"

Output: Broader search + keyword fallback.

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?
  • All results are first class cabin?

Any NO → re-execute from Step 2.

Usage Examples

flyai search-flight --origin "Beijing" --destination "Shanghai" --dep-date 2026-05-01 --seat-class-name first --sort-type 2
flyai search-flight --origin "Shanghai" --destination "Tokyo" --dep-date 2026-06-01 --seat-class-name first --journey-type 1 --sort-type 4

Output Rules

  1. Conclusion first — lead with best or cheapest first class option
  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, flight numbers, or cabin 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.

User Query CLI Parameter Mapping
"first class" / "头等舱" --seat-class-name first
"cheapest first class" / "最便宜头等舱" add --sort-type 3
"direct first class" / "直飞头等舱" add --journey-type 1 --sort-type 4
"round-trip first class" / "往返头等舱" add --back-date {date}

First class availability varies by route. Domestic trunk routes (BJ-SH, BJ-GZ) typically have 2-4 first class seats per flight. International long-haul may offer lie-flat suites. If 0 results, suggest business class as alternative.

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
Key things to consider before enabling this skill: - Verify the tool: the skill requires installing @fly-ai/flyai-cli from npm at runtime. Ask for the CLI's official homepage, source repository, or npm vendor verification before installing. Do not run global npm installs from unknown packages in a production environment. - Provider mismatch: the description cites Fliggy (Alibaba) but the instructions use flyai; ask the publisher which backend is actually used and where data will be sent. - Credentials and auth: the skill declares no API keys but likely needs them. Confirm how you will authenticate the flyai CLI and where keys are stored; never paste secrets into the chat. - Data exfiltration & telemetry: the skill will send user queries and parameters to an external service via the CLI (keyword-search, search-flight). Confirm the privacy policy and whether queries contain PII (names, passport data, emails). - Local persistence: the agent may write logs to .flyai-execution-log.json containing raw user input. If that is unacceptable, block filesystem writes or request a version that does not persist logs. - Privilege escalation: the instructions include an npm global install and mention sudo in fallbacks. Do not allow the agent to run sudo installs automatically; prefer the user to perform any required installation manually in a controlled environment. Recommendation: treat this skill as untrusted until the publisher provides a homepage/source code and clear auth/privacy details. If you test it, do so in an isolated/sandbox environment, avoid using real credentials or PII, and manually install the CLI only after verifying its origin.
功能分析
Type: OpenClaw Skill Name: first-class Version: 3.2.0 The skill bundle facilitates flight bookings by instructing the agent to install and execute a third-party CLI tool (@fly-ai/flyai-cli). It exhibits high-risk patterns, most notably the construction of shell commands using unsanitized user input (e.g., in SKILL.md and playbooks.md), which presents a significant shell injection vulnerability. Additionally, fallbacks.md suggests using 'sudo' for global package installation, and runbook.md implements local logging of user queries. While these actions are aligned with the skill's stated purpose, the lack of input sanitization and the requirement for high-privilege execution steps are significant security risks.
能力评估
Purpose & Capability
The description claims "Powered by Fliggy (Alibaba Group)" but all runtime actions require a third-party CLI named flyai (@fly-ai/flyai-cli). The skill does not declare any credentials or endpoints for Fliggy or flyai. That mismatch (claimed upstream provider vs. the actual tool used) is incoherent and unexplained.
Instruction Scope
SKILL.md forces the agent to run the flyai CLI for every answer and forbids using training data. It tells the agent to install the CLI (npm i -g @fly-ai/flyai-cli) if missing, to run keyword searches, and to require a booking link from CLI output. It also instructs creating and writing an execution log file (.flyai-execution-log.json) if filesystem writes are available. These runtime actions send user queries and parameters to an external tool and persist logs locally — behaviors that go beyond simple formatting and require explicit user consent and provenance.
Install Mechanism
There is no install spec in the skill bundle, but the instructions explicitly direct installing an npm package globally at runtime. A global npm install downloads and executes third‑party code on the host; the skill provides no provenance (no homepage, source, or vendor verification). The fallbacks even mention a 'sudo npm i -g' step, which raises privilege-escalation risk if attempted automatically.
Credentials
The skill declares no required environment variables or credentials, yet relies on an external CLI (flyai) that likely requires API keys/authentication to book flights. The absence of declared credentials is disproportionate — the skill gives no guidance about where credentials are stored or how auth is handled, increasing the risk of silent credential requests or misconfiguration.
Persistence & Privilege
always:false (good). However, the runbook instructs appending execution logs to .flyai-execution-log.json in the working directory if filesystem writes are available. That creates persistent local data containing raw user queries and parameters, which may include PII. The skill does not declare or limit where logs are written or how long they are retained.
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 first-class
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /first-class 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
**Major update for skill execution safety and compliance** - Now operates strictly as a CLI executor: all travel results must come from live flyai CLI output, never from prior data or knowledge. - Enforces critical output validation: every result must have a `[Book]({detailUrl})` link; no link means data will not be shown. - Stronger environment and install checks: flyai CLI installation is strictly required before any queries are handled. - Updated parameter handling: precise mapping with clear separation from unsupported query types (e.g., business class redirected elsewhere). - Extended playbooks and fallback handling to cover broader real-world scenarios and error recovery. - Adds strict output formatting rules and user guidance for transparent, real-time, and trustworthy travel booking information.
元数据
Slug first-class
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

first-class 是什么?

Book first class flights, premium cabin tickets and luxury airline seats with lie-flat beds and lounge access. Also supports: flight booking, hotel reservati... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 72 次。

如何安装 first-class?

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

first-class 是免费的吗?

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

first-class 支持哪些平台?

first-class 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 first-class?

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

💬 留言讨论