← 返回 Skills 市场
64
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install rental-advisor
功能描述
AI rental advisor skill to help users make rental decisions. Triggers when users ask for rental area recommendations, property search, rent price estimation,...
安全使用建议
This skill's content (area guides, pricing methodology, contract checklist) aligns with a rental adviser. However, SKILL.md expects live searches using tools (e.g., `wechat-article-search`, `node scripts/search_wechat.js`) that are not included or declared. Before installing: 1) Confirm what runtime provides the referenced search tools or scripts — if none, the skill's 'live search' behavior won't work. 2) Ask the publisher/source for the missing scripts or an install spec. 3) Ensure your agent runtime is sandboxed and that you consent to any network access the skill may attempt (it may call external websites like WeChat/Xiaohongshu). 4) Do not provide sensitive personal data to any live-search steps without knowing how results are fetched/stored. If you need a quick check: treat this as a reference-only skill (using the static files) unless the author supplies the missing tooling and documents what network calls will be made.
功能分析
Type: OpenClaw Skill
Name: rental-advisor
Version: 1.0.3
The skill bundle provides a comprehensive rental advisory service but contains high-risk instructions in SKILL.md and references/pricing.md, explicitly directing the AI agent to use 'exec + curl' for web scraping. This pattern introduces a significant command injection vulnerability if the agent processes unsanitized user input (like community names or URLs) into shell commands. While these capabilities are aligned with the stated purpose of searching for live property listings, the use of raw execution for network requests is a high-risk practice compared to safer alternatives.
能力标签
能力评估
Purpose & Capability
The name, description, and included reference files (city guides, pricing methodology, contract checklist) are consistent with a rental advisor. However, the SKILL.md repeatedly instructs the agent to run live searches using tools like `wechat-article-search` and `node scripts/search_wechat.js` even though the skill declares no required binaries, no install steps, and provides no such scripts. This is a mismatch between the stated capability (live-data search) and what the bundle actually supplies.
Instruction Scope
Instructions are mostly scoped to rental recommendations, price estimation, and contract review. They do direct the agent to perform live searches on third‑party platforms (WeChat articles, Xiaohongshu) and to run example command lines. The SKILL.md does not instruct the agent to read unrelated system files or to exfiltrate credentials, but it does rely on external web searches and unspecified tooling — which could cause the agent to attempt network calls or local command execution depending on runtime privileges.
Install Mechanism
There is no install spec (instruction-only), which is low-risk in principle. However, the documentation includes explicit sample commands that assume the presence of a `wechat-article-search` tool and Node scripts; those artifacts are not included in the package. This gap is a practical incoherence: either the skill expects platform-provided tools (not documented) or the author omitted required files/install steps.
Credentials
The skill requests no environment variables, no credentials, and no config paths. That is proportionate for a read-only advisory skill. There are no declared sensitive requirements such as cloud keys or tokens.
Persistence & Privilege
The skill does not request permanent presence (always:false) and uses default autonomous invocation settings. It does not declare any behavior that would modify other skills or system settings. No elevated persistence privileges are requested.
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 rental-advisor - 安装完成后，直接呼叫该 Skill 的名称或使用
/rental-advisor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
v1.0.3: Split area reference into city-specific files (shanghai.md, beijing.md, shenzhen.md, guangzhou.md). Updated SKILL.md to reference new city file structure.
v1.0.2
v1.0.2: Remove static rent pricing tables. Pricing reference now focuses on live search methodology only. Areas reference now contains area characteristics only, no pricing data.
v1.0.1
v1.0.1: Add mandatory requirement confirmation step before recommendations. Require city, unit type, shared/whole, budget, commute location, frequency, and special requirements before providing answers. Update live market data for Shanghai Wujing/Zizhu area.
v1.0.0
Initial release: AI rental advisor with area recommendation, property search, price estimation, and contract review.
元数据
常见问题
Rental Advisor 是什么？
AI rental advisor skill to help users make rental decisions. Triggers when users ask for rental area recommendations, property search, rent price estimation,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 64 次。
如何安装 Rental Advisor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install rental-advisor」即可一键安装，无需额外配置。
Rental Advisor 是免费的吗？
是的，Rental Advisor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Rental Advisor 支持哪些平台？
Rental Advisor 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 Rental Advisor？
由 Frank2025（@fanghou2025）开发并维护，当前版本 v1.0.3。
推荐 Skills