Skip to main content
ZICQ

Skills ZICQ category:Documents mx-finance-data OpenClaw

Mx Finance Data

Based on the Eastern Wealth Database, which supports the search of financial data in natural languages and covers a wide range of assets, including real-time situations, company information, valuations, financial statements, etc., that can be used for investment research, trade re-entry, market monitoring, industry analysis, credit research, financial audit, asset allocation, etc., and for adaptation institutions and individuals. Returns a result that contains xlsx with a Markdown file. It involves L1/L2 data, companies and valuations.

781 installs · 73 stars

Official URL:ClawHub

What this skill does

Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.

When to use it

The official description does not include a separate “Use when”. Per the spec, agents activate this skill when the task matches keywords in that description.

How agents load it

Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: 金融数据查询; 密钥来源与安全说明; 功能范围; 1. 支持查询的对象范围; 2. 支持查询的数据类型; 3. 查询方式与处理逻辑.

File analysis

File analysis: besides SKILL.md, the body references scripts/get_data.py. Those resources load on demand.

Official description (original)

基于东方财富数据库,支持自然语言查询金融数据,覆盖A港美、基金、债券等多种资产,含实时行情、公司信息、估值、财务报表等,可用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景,适配机构与个人多元需求。返回结果包含 xlsx 与 Markdown 文件。Natural language query for financial data across all markets, including A-shares, ETFs, bonds, Hong Kong and US stocks, and funds. It provides L1/L2 data, financial indicators, company profiles and valuation metrics. Ideal for investment research, strategy backtesting, market monitoring and industry analysis. It meets the needs of diverse institutions and individuals.

金融数据查询密钥来源与安全说明功能范围1. 支持查询的对象范围2. 支持查询的数据类型3. 查询方式与处理逻辑4. 输出结果前提条件1. 注册东方财富妙想账号2. 配置 TokenmacOS 添加到 ~/.zshrc,Linux 添加到 ~/.bashrc3. 安装依赖

Source category:ClawHub Investment

SKILL.md & Agent activation

Official spec ↗
name
mx-finance-data
description
基于东方财富数据库,支持自然语言查询金融数据,覆盖A港美、基金、债券等多种资产,含实时行情、公司信息、估值、财务报表等,可用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景,适配机构与个人多元需求。返回结果包含 xlsx 与 Markdown 文件。Natural language query for financial data across all markets, including A-shares, ETFs, bonds, Hong Kong and US stocks, and funds. It provides L1/L2 data, financial indicators, company profiles and valuation metrics. Ideal for investment research, strategy backtesting, market monitoring and industry analysis. It meets the needs of diverse institutions and individuals.
  1. DiscoverThe client exposes names and descriptions to the agent.
  2. ActivateYour request or the task context selects the skill and loads its instructions.
  3. Load resourcesReferenced scripts, documentation and assets are used when needed.
Files referenced by the instructions · 1
  • scripts/get_data.py

These paths are extracted from the text. Check the upstream package to verify the files exist.

Invocation syntax and available tools depend on your Agent client. Client integration guide ↗

Install this skill

Skills CLI ↗

Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.

This skill references supporting files. Retrieve the complete directory from the source; copying SKILL.md alone may leave missing dependencies.

Ask your Agent to install

Copy these instructions to a compatible agent and confirm the target directory matches your client.

Install the agent skill "mx-finance-data" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-44400180165b3568-Mx-Finance-Data.html
Save it as .cursor/skills/mx-finance-data/SKILL.md or .claude/skills/mx-finance-data/SKILL.md and keep the frontmatter name and description exactly as-is.
This skill also ships scripts/, references/, or assets/ — fetch the whole folder from https://clawhub.ai/skills/mx-finance-data instead of creating only a SKILL.md.

No unambiguous GitHub package URL is recorded. Follow the original source's installer instructions.

ClawHub ↗

Readable layout

name: mx-finance-data description: 基于东方财富数据库,支持自然语言查询金融数据,覆盖A港美、基金、债券等多种资产,含实时行情、公司信息、估值、财务报表等,可用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景,适配机构与个人多元需求。返回结果包含 xlsx 与 Markdown 文件。Natural language query for financial data across all markets, including A-shares, ETFs, bonds, Hong Kong and US stocks, and funds. It provides L1/L2 data, financial indicators, company profiles and valuation metrics. Ideal for investment research, strategy backtesting, market monitoring and industry analysis. It meets the needs of diverse institutions and individuals. metadata: { "openclaw": { "requires": { "env":["EM_API_KEY"] }, "install": [ { "id": "pip-deps", "kind": "python", "package": "httpx pandas openpyxl", "label": "Install Python dependencies" } ] } }

金融数据查询

密钥来源与安全说明

  • 本技能仅使用一个环境变量:EM_API_KEY。
  • EM_API_KEY 由东方财富妙想服务(https://ai.eastmoney.com/mxClaw)签发,用于其接口鉴权。
  • 在提供密钥前,请先确认密钥来源、可用范围、有效期及是否支持重置/撤销。
  • 禁止在代码、提示词、日志或输出文件中硬编码/明文暴露密钥。

功能范围

1. 支持查询的对象范围

  • 股票(A 股、港股、美股)
  • 板块、指数、股东
  • 企业发行人、债券、非上市公司
  • 股票市场、基金市场、债券市场

2. 支持查询的数据类型

支持查询以下类型的结构化数据:

  • 实时行情(现价、涨跌幅、盘口数据等)
  • 量化数据(技术指标、资金流向等)
  • 报表数据(营收、净利润、财务比率等)

3. 查询方式与处理逻辑

统一使用 --query 传入自然语言问句(包含实体与指标),并使用 --indicators 传入从问句中提取的金融指标等关键信息。Skill 会先对 query 做实体识别,再按识别结果选择查数路径:

  • 识别实体数 ≤ 5:直接查数
  • 识别实体数 > 5:批量查数,最多处理识别结果中的前 500 个有效实体,如需大于500个实体,可分批多次调用

注意:当用户问句中只包含代词,需结合上下文或者提供文件读取所有实体名称,一并输入query。

--indicators 参数说明

调用本 Skill 前,需根据 --query 从用户问句中提取需要查询的金融指标(或指标组),填入 --indicators:

  • 只填指标和时间范围等除实体外所有有效信息,不含实体名称等修饰语。
  • 多个指标用用户原话拼接,如 市盈率(动)和总市值、涨跌幅、营收、毛利、净利。
  • 不要在 --indicators 里重复写实体。
  • 尽量用用户原话表述,不要二次改写。

示例
用户问「查询贵州茅台、五粮液近一年营收」
→ --query "查询贵州茅台、五粮液近一年营收" --indicators "近一年营收"

用户问「这批股票的涨跌幅是多少」或列出 6 只以上股票
→ --query "查询 A、B、C、D、E、F 六只股票的涨跌幅、pe、市值" --indicators "涨跌幅、pe、市值"

4. 输出结果

Skill 执行后会输出两个文件:

  • Excel(.xlsx):多 sheet 结构化数据表,每个实体/指标组合对应一个 sheet
  • Markdown(.md):与 Excel 内容一致的 Markdown 表格,按 sheet 分二级标题

前提条件

1. 注册东方财富妙想账号

访问 https://ai.eastmoney.com/mxClaw 注册账号并获取API_KEY。

2. 配置 Token

# macOS 添加到 ~/.zshrc,Linux 添加到 ~/.bashrc
export EM_API_KEY="your_api_key_here"

然后根据系统执行对应的命令:

macOS:

source ~/.zshrc

Linux:

source ~/.bashrc

3. 安装依赖

pip3 install httpx pandas openpyxl --user

快速开始

在工作目录下执行:

python3 {baseDir}/scripts/get_data.py --query "贵州茅台近期走势如何" --indicators "近期走势"

多实体示例:

python3 {baseDir}/scripts/get_data.py --query "查询贵州茅台、五粮液、宁德时代、比亚迪、隆基绿能、中芯国际的市盈率(动)" --indicators "市盈率(动)"

参数说明:

| 参数 | 必填 | 默认值 | 说明 | | --- | --- | --- | --- | | --query | 是 | - | 自然语言查询问句,需包含所有查询实体名称| | --indicators | 是 | - | 从 query 中提取的金融指标、时间范围等关键信息|


输出示例

直接查数:

识别实体数: 1
查数模式: 直接查数
返回实体数: 1
文件: /path/to/miaoxiang/mx_finance_data/mx_finance_data_9535fe18.xlsx
Markdown: /path/to/miaoxiang/mx_finance_data/mx_finance_data_9535fe18.md
表格行数: 42

多实体查数:

识别实体数: 128
查数模式: 多实体
返回实体数: 128
文件: /path/to/miaoxiang/mx_finance_data/mx_finance_data_a1b2c3d4.xlsx
Markdown: /path/to/miaoxiang/mx_finance_data/mx_finance_data_a1b2c3d4.md
表格行数: 150

输出文件说明

| 文件 | 说明 | | --- | --- | | mx_finance_data_<查询id>.xlsx | 结构化数据表,包含请求的实体与指标 | | mx_finance_data_<查询id>.md | 与 Excel 内容一致的 Markdown 表格 |

常见问题

错误:请设置 EM_API_KEY 环境变量

  • 请访问 https://ai.eastmoney.com/mxClaw 获取API_KEY。
  • 配置EM_API_KEY环境变量

多实体查数报错:缺少 --indicators

  • 识别实体数 > 5 时必须提供 --indicators,否则无法构造有效的查数问句。

当前一次请求的数据量过大,部分数据可能会有缺失,请减少指标数量和查询日期范围

  • 可分批多次(分不同指标或者日期)调用该技能,一次性请求压力过大。

多实体查数最多处理识别结果中前 500 个有效实体

  • 可分批多次(每次500个实体数量以内)调用该技能

Related skills

Documents

Ontology

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, …

Documents

Nano Pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Documents

Word / DOCX

Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and co…

Documents

Baidu Search

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.