← 返回 Skills 市场

Housing Price Data

Name: Housing Price Data
Author: fangtianwd

作者 Fangtianwd · GitHub ↗ · v2.2.3 · MIT-0

cross-platform ✓ 安全检测通过

217

总下载

当前安装

版本数

在 OpenClaw 中安装

/install housing-price-data

功能描述

Fetch official Chinese 70-city residential property price index data from the National Bureau of Statistics (国家统计局). Use when users ask about 房价指数, housing t...

使用说明 (SKILL.md)

中国70城住宅价格指数数据技能

本技能通过国家统计局 RSS 抓取《70个大中城市商品住宅销售价格变动情况》，返回可直接供 agent 总结的结构化数据。

依赖：Python 3、requests、beautifulsoup4，以及在需要图表时可用的 matplotlib。运行时需要能访问 stats.gov.cn。

何时使用

用户问某个 70 城城市最近房价走势、环比/同比/定基指数
用户要看新建商品住宅或二手住宅的价格指数
用户要最新一期官方数据，或指定近几期历史数据
用户需要图表辅助分析

快速流程

先告知用户正在从国家统计局获取官方数据。
判断需求是“最新一期”还是“历史走势”：
- 最新一期：使用 --latest
- 历史走势：使用 --limit \x3CN>
运行脚本：

python3 scripts/fetch_data.py --city \x3C城市> --metrics \x3C指标> --latest
python3 scripts/fetch_data.py --city \x3C城市> --metrics \x3C指标> --limit 24
python3 scripts/fetch_data.py --city \x3C城市> --chart --limit 24

读取 JSON 输出中的顶层字段，再决定如何组织回答。
以表格或简短摘要呈现，不要把原始 JSON 直接贴给用户，除非用户明确要求。

常用参数

--city：目标城市，支持常见输入变体，如 北京市
--metrics：逗号分隔，支持 环比、同比、定基
--latest：只返回最新一期
--limit：返回最近 N 期历史数据
--chart：生成图表
--output：图表输出路径
--no-cache：禁用缓存

指标别名可直接输入：mom、yoy、环比指数、同比指数、fixed-base。

输出重点

重点看这些字段：

requested_city：用户请求的城市输入
matched_city：脚本最终匹配到的规范城市名
latest_period：本次结果中的最新期次
record_count：返回记录数
records：核心数据

records 中每条记录包含：

period
city
indicator
metrics
source_url

呈现建议

默认优先展示最新一期或最近几期结果
指标名可简写为：
- 新建商品住宅销售价格指数 -> 新建商品住宅
- 二手住宅销售价格指数 -> 二手住宅
指数以 100 为基准：
- 高于 100 表示上涨
- 低于 100 表示下降

示例

python3 scripts/fetch_data.py --city 武汉 --metrics 环比,同比 --latest
python3 scripts/fetch_data.py --city 上海市 --metrics yoy --limit 12
python3 scripts/fetch_data.py --city 北京 --metrics 环比,同比 --chart --limit 24

参考资料

城市列表和指标说明：references/REFERENCE.md
数据来源：国家统计局 RSS 与公告正文
注意：这里是价格指数，不是绝对房价

注意事项

国家统计局通常在每月中旬发布上月数据
网络受限时可能出现 RSS 或详情页抓取失败
图表默认保存到当前 skill 目录，可用 --output 覆盖

安全使用建议

This skill appears internally consistent and does what it says: it fetches the National Bureau of Statistics RSS and parses official announcement pages to extract 70‑city price‑index data. Before installing, consider: (1) the scripts will make outbound HTTP requests to stats.gov.cn (ensure your environment/network policy allows that and you trust that site); (2) the package includes a snapshot artifact (artifacts/full-dataset.json) which is a local data copy — review it if you care about stale data or included content; (3) dependencies must be installed (requests, beautifulsoup4, matplotlib) — install in a virtualenv or sandbox; (4) the skill source/owner is unknown — if provenance matters, you may want to run the tests locally (provided) to inspect behavior yourself. No environment variables or secret access are requested and there are no obvious exfiltration endpoints in the code.

功能分析

Type: OpenClaw Skill Name: housing-price-data Version: 2.2.3 The skill bundle is a legitimate tool designed to fetch and visualize housing price index data from the Chinese National Bureau of Statistics (stats.gov.cn). The Python scripts (fetch_data.py, validate_full_data.py) use standard libraries like requests and BeautifulSoup to parse RSS feeds and HTML tables, and matplotlib for data visualization. No evidence of data exfiltration, malicious execution, or prompt injection was found; all network activity is restricted to the official government domain, and the code logic strictly follows the stated purpose.

能力评估

✓ Purpose & Capability

Name/description (fetch official 70-city 房价指数) match the packaged code and docs: scripts fetch the stats.gov.cn RSS, parse announcement pages, extract city/metric tables, and optionally build charts. Declared dependencies (requests, beautifulsoup4, matplotlib) and packaged files are appropriate for that task.

✓ Instruction Scope

SKILL.md instructs running the included Python scripts to fetch RSS and parse pages on stats.gov.cn and to generate charts or JSON. The runtime instructions do not ask the agent to read unrelated system files, environment secrets, or send data to endpoints other than the official stats site (the code fetches URLs discovered in the RSS). The skill cautions about network reachability and describes outputs.

✓ Install Mechanism

There is no install spec (instruction-only runtime), and included requirements.txt lists common PyPI packages. No downloads from untrusted URLs or archives; code is bundled with the skill. Risk from install actions is low.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. The code does make outbound HTTP requests to RSS and announcement pages (expected). No secret access or unrelated credential requests are present.

✓ Persistence & Privilege

Flags show always: false and normal agent invocation allowed. The skill does not request permanent platform-wide privileges, does not modify other skills' configs, and stores only local in-memory cache and optional output files in the skill directory as documented.

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 housing-price-data
安装完成后，直接呼叫该 Skill 的名称或使用 /housing-price-data 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

v2.2.3

- Updated SKILL.md version number to 2.2.3. - No other content changes; documentation remains the same.

v2.2.2

Version 2.2.2 of housing-price-data - No file or documentation changes detected in this version. - Functionality, documentation, and metadata remain unchanged from version 2.2.1.

v2.2.1

Refresh skill contents and publish latest local updates.

v2.2.0

新增城市别名、指标别名、--latest参数、全量数据校验、单元测试

v2.1.0

初始版本发布

元数据

Slug housing-price-data

版本 2.2.3

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 5

常见问题