← 返回 Skills 市场
rollinggo-hotel
作者
dreamtzlong
· GitHub ↗
· v1.0.3
· MIT-0
320
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install rollinggo-hotel
功能描述
Hotel search and pricing via the RollingGo CLI. Use when the user wants to search hotels by destination, filter by date/star/budget/tags/distance, inspect ho...
安全使用建议
This skill is internally consistent for running the RollingGo CLI and only needs one API key. Before installing: (1) Confirm you trust the rollinggo npm/PyPI package publisher (npm install / npx executes registry code). Using npx/uvx --package fetches the latest code each run — consider pinning a vetted version if you prefer lower supply-chain risk. (2) Provide the RollingGo_API_KEY only to this skill (prefer per-skill injection rather than host-wide env). (3) If you run in a sandbox, follow the host's secure injection method rather than exporting keys in shared shells. (4) If you need stronger assurance, review the rollinggo package source or publisher reputation on the registry before granting the API key.
功能分析
Type: OpenClaw Skill
Name: rollinggo-hotel
Version: 1.0.3
The rollinggo-hotel skill provides a CLI-based interface for searching hotels and retrieving pricing information via the RollingGo service (mcp.agentichotel.cn). It utilizes standard package managers like npm (npx) and uv (uvx) to execute the 'rollinggo' package and requires a dedicated API key (RollingGo_API_KEY). The instructions in SKILL.md and the reference files are well-documented and align strictly with the stated hotel-search functionality without any indicators of malicious intent, unauthorized data access, or harmful prompt injections.
能力标签
能力评估
Purpose & Capability
Name/description, required binaries (rollinggo/npx/node/uvx/uv) and the single required env var (RollingGo_API_KEY) all align with a CLI wrapper that can run either a Node or uvx/Python-based rollinggo package. The install entry installs the rollinggo npm package, which is consistent with the described behavior.
Instruction Scope
SKILL.md instructs only how to run the rollinggo CLI (search-hotels, hotel-detail, hotel-tags), how to supply the API key, and how to handle outputs/errors. It does not instruct reading unrelated files, harvesting other environment variables, or transmitting data to unexpected endpoints. The guidance about injecting the API key into host/sandbox config is operational but expected for a hosted agent environment.
Install Mechanism
Install uses npm (rollinggo@latest) and the SKILL.md recommends npx/uvx --package/--from rollinggo@latest, which is expected for a CLI tool. This is moderate-risk compared with instruction-only skills because it will execute code from the npm/PyPI registries and the skill's default is 'always fetch latest' (npx/uvx/upgrade). That behavior is coherent with the stated goal but increases supply-chain risk vs. a pinned version.
Credentials
Only RollingGo_API_KEY is required and is declared as the primary credential. The referenced host-injection instructions explain ways to persist the key for sandboxed runs; that is operational guidance but does not request unrelated credentials or broaden scope beyond the single API key.
Persistence & Privilege
Skill is not always-enabled and is user-invocable; it allows autonomous invocation (normal default). The skill does not request to modify other skills or system-wide settings. Advice about adding the API key to host config is informational, not an automatic privilege escalation.
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 rollinggo-hotel - 安装完成后，直接呼叫该 Skill 的名称或使用
/rollinggo-hotel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
v1.0.3
- Added reference: claw-host-env.md for API key persistence guidance.
- Updated install instructions to always use rollinggo@latest for npm and uv tools.
- Improved runtime guidance: reference files and API key persistence recommendation are now clarified.
- Minor metadata adjustments for skill identification and environment setup.
v1.0.2
- Skill name changed from "rollinggo-hotel" to "rollinggo-searchhotel"
- API key environment variable updated from AIGOHOTEL_API_KEY to RollingGo_API_KEY
- Default policy updated to always use the latest version of the RollingGo CLI on each run
- Added step-by-step upgrade/refresh instructions for both npm/npx and uvx environments
- No code or logic changes detected; documentation and environment setup only
v1.0.1
### rollinggo-hotel v1.0.1
- Updated skill documentation for improved brevity and clarity, with streamlined usage instructions and quick command reference.
- Added a metadata block for improved integration and installing guidance across both Node and Python environments.
- Default behavior and trigger scenarios are now explicitly stated for reliable skill invocation.
- Clarified filtering, tag matching, and workflow steps for hotel lookup and detail inspection.
- Removed: unnecessary agent configuration file (agents/openai.yaml) for a leaner distribution.
v1.0.0
- Initial release of rollinggo-hotel skill.
- Supports hotel search, filtering, tag inspection, and hotel detail lookups using the RollingGo CLI.
- Prioritizes the npm/npx distribution for hotel lookup unless the user explicitly requests Python (uv) distribution.
- Guides users through typical workflows: search hotels, apply filters, inspect tags, fetch pricing/details, and interpret CLI output.
- Defines clear output rules and exit codes, with preference for JSON output to support automation.
- Includes parity checklist for Node and Python CLI distributions to help with comparison and compatibility validation.
元数据
常见问题
rollinggo-hotel 是什么？
Hotel search and pricing via the RollingGo CLI. Use when the user wants to search hotels by destination, filter by date/star/budget/tags/distance, inspect ho... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 320 次。
如何安装 rollinggo-hotel？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install rollinggo-hotel」即可一键安装，无需额外配置。
rollinggo-hotel 是免费的吗？
是的，rollinggo-hotel 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
rollinggo-hotel 支持哪些平台？
rollinggo-hotel 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 rollinggo-hotel？
由 dreamtzlong（@dreamtzlong）开发并维护，当前版本 v1.0.3。
推荐 Skills