← 返回 Skills 市场
104
总下载
2
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install travel-emergency-assistant
功能描述
在航班取消、酒店超售、景点关闭等行中突发场景下，一键生成含实时价格、预订链接、决策理由的「应急三选一」方案。聚焦高焦虑场景，提供情绪安抚 + 行动指引（最晚下单时间 + 交通接驳），而非单纯参数对比。适用于旅行途中遇到意外需要快速决策的场景。
安全使用建议
This skill is coherent: it delegates searches to a FlyAI CLI and otherwise asks for no secrets. Before installing or letting an agent run it: (1) Verify the @fly-ai/flyai-cli package (npm page, GitHub repo, maintainer) so you trust its provenance; (2) avoid running global npm installs with sudo unless you trust the package—prefer inspecting the package or running it in a contained environment; (3) be aware the agent will run shell commands (which/npm/flyai) and the CLI will make network requests to fetch live pricing/links; (4) confirm any booking/financial actions yourself—this skill provides guidance and links but should not be allowed to make payments automatically. If you cannot verify the FlyAI CLI source, treat the installation step as high risk and do not proceed.
能力评估
Purpose & Capability
The skill is an instruction-only travel emergency assistant and all declared runtime actions (searching flights/hotels/POI) map to calling a FlyAI CLI; asking for no env vars or unrelated system access is coherent with its purpose.
Instruction Scope
The SKILL.md explicitly requires checking for and (if absent) installing and running the FlyAI CLI via shell commands (which flyai, npm install -g, flyai search-*). This requires executing system commands and network calls to the npm registry; the instructions do not ask the agent to read unrelated local files or secrets, but they do mandate installing and invoking an external binary.
Install Mechanism
No packaged install spec is bundled; instead the document instructs installing @fly-ai/flyai-cli from the public npm registry with npm install -g. Installing a global npm package is a moderate-risk operation (runs arbitrary code from npm) and should be validated (check package source, maintainers, and repository) before performing.
Credentials
The skill declares no environment variables, no credentials, and no access to unrelated config paths. That aligns with the stated functionality (it delegates data retrieval to the FlyAI CLI).
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system-wide configuration edits or access to other skills' credentials. The agent will need permission to run shell commands to install/execute the CLI, which is expected for this design.
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 travel-emergency-assistant - 安装完成后，直接呼叫该 Skill 的名称或使用
/travel-emergency-assistant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
v1.0.1
- Skill renamed from "travel-emergency-assistant" to "trip-emergency-lite"
- Version reset to 1.0.0 in SKILL.md (previously 1.0.0 for "travel-emergency-assistant")
- New section added detailing the mandatory FlyAI CLI installation check and error handling before any search
- Output logic clarified: must not use fallback/demo data; explicitly quit and instruct user to install dependencies if CLI missing
- Documentation streamlined; some scenario-specific outputs, details, and file structure remain, but now tightly focused on FlyAI CLI dependency and search execution flow
v1.0.0
行程急救包 1.0.0 首次发布，为旅行中突发状况一键生成应急三选一决策方案：
- 支持航班取消/延误、酒店超售/满房、景点临时关闭等应急场景识别
- 自动从用户输入提取出发地、目的地、时间、预算、特殊需求等关键信息
- 实时调用 FlyAI 工具，输出含价格、预订链接、最晚下单时间和详细优劣势的三选一卡片
- 针对高焦虑场景，结合情绪安抚、风险提示和个性化决策建议
- 支持中文极简输入，30秒内生成最优可行决策
元数据
常见问题
travel-emergency-assistant 是什么？
在航班取消、酒店超售、景点关闭等行中突发场景下，一键生成含实时价格、预订链接、决策理由的「应急三选一」方案。聚焦高焦虑场景，提供情绪安抚 + 行动指引（最晚下单时间 + 交通接驳），而非单纯参数对比。适用于旅行途中遇到意外需要快速决策的场景。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 104 次。
如何安装 travel-emergency-assistant？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install travel-emergency-assistant」即可一键安装，无需额外配置。
travel-emergency-assistant 是免费的吗？
是的，travel-emergency-assistant 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
travel-emergency-assistant 支持哪些平台？
travel-emergency-assistant 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 travel-emergency-assistant？
由 Uasnu1111（@uasnu1111）开发并维护，当前版本 v1.0.1。
推荐 Skills