← 返回 Skills 市场
Flyai Super Train / 火车票智能中转
作者
zhangxchao
· GitHub ↗
· v1.0.4
· MIT-0
209
总下载
2
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install super-train
功能描述
火车票智能中转方案推荐助手。查火车票/高铁票/动车票/12306余票，智能拼接中转换乘方案，学习用户偏好（坐席策略、时间偏好、中转约束）。火车票查询/余票/车次/预订/中转换乘/坐席偏好。
安全使用建议
This skill appears to do what it claims: it calls the external flyai CLI to search trains and keeps local preference/history JSON files. Before using: (1) verify you trust and review the @fly-ai/flyai-cli npm package before installing it globally; (2) be aware history.json will record searches/purchases and may include personal travel data — clear or secure it if needed; (3) the skill may call external APIs via the CLI (optionally using a FLYAI_API_KEY) so only set that key if you trust the service; (4) the SKILL.md includes explicit input sanitization to reduce shell-injection risks, but installing and running an external CLI is the main trust boundary — review that tool's security/privacy policy.
功能分析
Type: OpenClaw Skill
Name: super-train
Version: 1.0.4
The 'super-train' skill is a legitimate train ticket search and recommendation assistant. It utilizes the 'flyai-cli' tool and includes robust security instructions in SKILL.md, specifically defining input validation rules and character whitelists to prevent shell injection attacks. The skill limits its file operations to local asset files (preferences.json and history.json) and shows no signs of data exfiltration, unauthorized execution, or malicious prompt injection.
能力评估
Purpose & Capability
Name/description describe train ticket search, transfer stitching and preference learning; the SKILL.md only requires the flyai CLI and local preference/history files and optionally an API key from flyai.open.fliggy.com — these are appropriate for the stated functionality.
Instruction Scope
Runtime instructions are detailed and scoped to calling the external flyai CLI, reading/writing assets/preferences.json and assets/history.json, and validating user inputs before building CLI arguments. The skill explicitly forbids reading/writing other filesystem paths and includes shell-injection protections. Note: it will persist user query/purchase history in assets/history.json (potentially sensitive).
Install Mechanism
This is an instruction-only skill with no install spec. It expects the user to have installed @fly-ai/flyai-cli via npm -g. That dependency is reasonable for the described purpose, but installing an external global npm package carries independent trust/risk decisions that the user should evaluate before installing.
Credentials
The skill requests no environment variables or credentials by default. It mentions an optional FLYAI_API_KEY for improved results (which aligns with the external service). There are no unrelated or excessive credential requests.
Persistence & Privilege
always:false (no forced presence). The only persistent state is the two local asset files inside the skill directory (preferences.json, history.json), which the skill documents and limits itself to. It does not request system-wide configuration changes or other skills' credentials.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install super-train - 安装完成后，直接呼叫该 Skill 的名称或使用
/super-train触发 - 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
v1.0.4
No file changes detected; documentation refinements.
- Revised and clarified description of the scheme评分维度 (scoring dimensions) section for greater detail and accuracy.
- Improved language clarity and readability throughout SKILL.md, with minor adjustments to formatting and examples.
- No changes to functionality or logic—documentation update only.
v1.0.3
super-train v1.0.3 Changelog
- SKILL.md 文档增强：新增“配置”章节，说明试用无需 API Key，可选绑定 key 更佳体验，并给出设置命令指引。
- 其余功能和工作流、输出格式、用户引导规范，均与上一版本保持一致。
v1.0.2
super-train v1.0.2
- 增加所有用户输入参数的严格安全校验，防止 shell 注入等安全风险
- 明确城市名、日期、小时、车次号等参数的合法字符集和格式限制
- 命令调用前，参数必须用双引号包裹，所有不合规输入将被拒绝并提示用户
- 仅允许读写指定的数据文件，写入前验证 JSON 合法性
- 文档中新增“输入安全校验”板块，细化输入校验和拒绝策略
- 其他原有功能与流程无变化
v1.0.1
**Summary:**
This update removes the learned preferences (learned.json) feature, simplifying user preference handling and workflow.
- 移除 assets/learned.json 文件，停止自动归纳历史偏好，所有偏好仅通过用户显式设定 (preferences.json) 管理。
- 删除与隐式偏好学习、归纳、加权相关的流程与规则说明。
- 精简用户数据结构，保留仅 assets/preferences.json 与 assets/history.json。
- 部分自然语言说明、触发条件与流程示例更简明，避免重复与冗余表述。
- 提升首次使用、偏好处理、及中转推荐等交互流程的可操作性描述。
- skill 描述信息更明确，增加图标（icon: 🚄），便于识别。
v1.0.0
super-train 1.0.0 — 火车票智能中转推荐助手上线！
- 支持通过自然语言查询12306火车票及智能拼接中转方案，个性化记忆用户偏好。
- 集成 flyai-cli，实现直达与智能中转分步查询，支持偏好与行为历史双重记忆。
- 按优先级智能读取/归纳用户偏好，并引导收集必填查询参数。
- 细化中转、坐席、出发时段等过滤与推荐规则，符合实际出行场景。
- 查询结果以卡片/多方案表格方式规范展示，包含推荐理由与真实接口数据。
- 自动记录查询历史及偏好，支持智能学习和偏好归纳。
- 明确支持对话模板与偏好冲突处理，优化多轮交互体验。
元数据
常见问题
Flyai Super Train / 火车票智能中转 是什么？
火车票智能中转方案推荐助手。查火车票/高铁票/动车票/12306余票，智能拼接中转换乘方案，学习用户偏好（坐席策略、时间偏好、中转约束）。火车票查询/余票/车次/预订/中转换乘/坐席偏好。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 209 次。
如何安装 Flyai Super Train / 火车票智能中转？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install super-train」即可一键安装，无需额外配置。
Flyai Super Train / 火车票智能中转 是免费的吗？
是的，Flyai Super Train / 火车票智能中转 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Flyai Super Train / 火车票智能中转 支持哪些平台？
Flyai Super Train / 火车票智能中转 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 Flyai Super Train / 火车票智能中转？
由 zhangxchao（@zhangxchao）开发并维护，当前版本 v1.0.4。
推荐 Skills