← Back to Skills Marketplace
hongweisong1999

travel-city-game(旅行游戏副本生成器)

by HongWeiSong1999 · GitHub ↗ · v1.0.9 · MIT-0
cross-platform ✓ Security Clean
328
Downloads
3
Stars
0
Active Installs
13
Versions
Install in OpenClaw
/install travel-city-game
Description
根据用户输入的城市名,自动调用 flyai 搜索该城市的景点、体验、美食产品, 然后生成一个游戏化的3节点叙事行程 H5 页面。每个节点包含 AI 生成的故事文案 和飞猪真实预订链接。使用方式: /travel-city-game 城市名。 当用户提到 "travel-city-game"、"生成行程"、"旅行叙...
Usage Guidance
This skill appears to do what it says: it uses the flyai CLI to gather product data and builds a local H5 page. Before installing: 1) Ensure you trust the flyai Skill/CLI (it will be invoked and may use your FLYAI_API_KEY if you configure one). 2) Note the skill expects python3 and will write preview HTML under an outputs/ directory and a PID file (~/.city-game-serve.pid) in your home; the serve script may send SIGTERM to a previous serve.py process only after verifying the process identity. 3) The manifest lists 'node' though Node.js isn't used by the included Python workflow — you can ignore Node unless you plan other integrations. 4) The SKILL.md advises safe subprocess use, but never run unexpected installation commands (it warns against auto-installing flyai). If you rely on flyai and are comfortable granting a CLI access to your FLYAI_API_KEY, this skill is coherent and proportionate.
Capability Analysis
Type: OpenClaw Skill Name: travel-city-game Version: 1.0.9 The skill bundle is a travel-themed game generator that uses the flyai CLI to fetch real-world travel data and creates an interactive H5 page. It exhibits strong security practices, including explicit instructions in SKILL.md to prevent shell injection and supply chain attacks, and the serve.py script includes path validation to prevent directory traversal. All functionalities, such as local file serving and external API calls, are well-documented and aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The skill's stated goal (call flyai to find products and produce an H5 game page) matches the instructions and included files. It requires the flyai CLI and python3 which are appropriate. Minor mismatch: the compatibility section lists 'node' as a required binary but SKILL.md and the included Python serve script do not require Node at runtime — this appears unnecessary.
Instruction Scope
SKILL.md instructs the agent to call the flyai CLI, parse JSON, generate stories, and render an HTML output under outputs/. It explicitly warns about shell-injection risks and prescribes safe subprocess usage. The instructions do not ask the agent to read unrelated files or exfiltrate data to unknown endpoints. They do advise the user to set FLYAI_API_KEY if rate-limited (see environment note).
Install Mechanism
There is no remote install step or arbitrary download. The skill ships as instruction + local files (template HTML and a Python serve script). No install URL or third-party archive is used, so installation risk is low.
Credentials
The skill's manifest lists no required environment variables, which is broadly proportional. SKILL.md, however, instructs users to set FLYAI_API_KEY if they encounter rate limits — this is reasonable for a CLI-backed integration but the manifest does not declare this optional credential. The skill does not request unrelated secrets.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. The included serve.py writes a PID file to the user's home (~/.city-game-serve.pid), attempts to detect and (only if identity matches) SIGTERM a previous instance, and opens a local HTTP server to preview generated HTML. These are expected for a local preview tool but involve writing a small PID file and sending SIGTERM to a verified process — users should be aware of this local footprint.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install travel-city-game
  3. After installation, invoke the skill by name or use /travel-city-game
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.12
No functional changes; documentation update only. - 移除了“内置测试 Key”自动补充和相关安全说明,要求用户自行设置 FLYAI_API_KEY。 - 精简并调整“API 限流处理”说明,强调需配置专属 API Key,flyai CLI 会自动使用。 - 其余工作流程、交互和生成规则保持不变。
v1.0.11
- 增加安全的 API Key 配置流程,优先使用用户自定义 Key,无 Key 时用 Base64 编码的内置测试 Key。 - 内置 Key 仅限额度有限的测试,编码存储避免明文暴露,用户配置后完全覆盖。 - 优化 API Key 限流处理及用户提示流程。 - 其余整体执行与功能流程保持不变。
v1.0.10
Version 1.0.10 - 增加了 flyai API Key 配置逻辑:如环境变量未设置,则自动使用内置默认 Key,提升首次使用成功率。 - 更新了限流提示和处理:检测到 API 被公共限流或额度耗尽时,引导用户获取并设置专属 API Key。 - 优化文档和流程,确保每次搜索前都会带有效 API Key,减少因未配置密钥导致的搜索失败。
v1.0.9
Version 1.0.9 - 强化供应链安全规范,不再自动安装 flyai CLI,要求用户提前安装 flyai Skill。 - 明确 flyai CLI 检查方式和错误提示,避免自动 npm 安装带来的潜在风险。 - 增加 flyai API 限流处理,指导用户获取和配置专属 API Key。 - 新增所有 shell 命令参数的注入安全要求,优先推荐 Python 子进程方式或单引号包裹参数。 - 更新 compatibility 字段,精确声明 flyai 依赖与安装指引,增加对 node、flyai 可执行文件的要求。 - 其余核心流程(搜索、节点组装、模板约束)保持不变。
v1.0.8
- Fix template.html
v1.0.7
- 新增 scripts/generate.py 脚本,统一负责模板渲染和 HTML 生成,确保界面输出与模板完全一致 - 工作流优化:节点和加载进度数据先写入临时 JSON 文件,再由 generate.py 处理,不再直接读写模板或 HTML - serve.py 本地预览服务的启动路径需严格按照 generate.py 输出的 OUTPUT_PATH 赋值,避免路径拼接错误 - 兼容性要求新增对 node 的依赖 - 明确禁止自行渲染 HTML,必须通过 generate.py 调用生成
v1.0.6
- Fix template.html
v1.0.5
- surge.sh 部署域名规范更新:要求 surge.sh 部署域名需用城市拼音(如 changsha、dali、xiamen),避免中文域名导致发布失败。 - 未检出功能代码调整,仅文档细节优化,更明确部署域名格式规范。 - 其余流程与用法保持不变。
v1.0.4
fix template.html
v1.0.3
No code or workflow changes in this version. - No file changes detected. - The skill’s features and instructions remain the same as in the previous version.
v1.0.2
- Skill 名称由 city-game 修改为 travel-city-game。 - 命令触发关键字由 /city-game 改为 /travel-city-game。 - 说明文、描述和触发指令中所有 city-game 相关内容全面替换为 travel-city-game,保持功能一致。 - 其余功能、流程与接口保持原样,无新增参数或核心逻辑变更。
v1.0.1
No user-visible changes in this version. - No file changes detected compared to the previous release. - Behavior and documentation remain the same as before.
v1.0.0
Initial release: generates interactive, narrative-driven H5 travel itineraries for any city using real product data. - Integrates flyai CLI to fetch live tickets, experiences, and food products by city. - Automatically creates a 3-node gamified story route, each step with immersive, city-specific AI-generated stories and real booking links. - Features "unexpected engine": if a product is sold out, triggers AI-powered search for alternatives and generates narrative twists. - Outputs a ready-to-share HTML journey with instant local web preview; supports one-click public deployment. - Activates on various user intents to generate city exploration routes, even from simple trip planning queries.
Metadata
Slug travel-city-game
Version 1.0.9
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 13
Frequently Asked Questions

What is travel-city-game(旅行游戏副本生成器)?

根据用户输入的城市名,自动调用 flyai 搜索该城市的景点、体验、美食产品, 然后生成一个游戏化的3节点叙事行程 H5 页面。每个节点包含 AI 生成的故事文案 和飞猪真实预订链接。使用方式: /travel-city-game 城市名。 当用户提到 "travel-city-game"、"生成行程"、"旅行叙... It is an AI Agent Skill for Claude Code / OpenClaw, with 328 downloads so far.

How do I install travel-city-game(旅行游戏副本生成器)?

Run "/install travel-city-game" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is travel-city-game(旅行游戏副本生成器) free?

Yes, travel-city-game(旅行游戏副本生成器) is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does travel-city-game(旅行游戏副本生成器) support?

travel-city-game(旅行游戏副本生成器) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created travel-city-game(旅行游戏副本生成器)?

It is built and maintained by HongWeiSong1999 (@hongweisong1999); the current version is v1.0.9.

💬 Comments