← Back to Skills Marketplace
lucasxing1

A股智投大师

by lucasxing1 · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
645
Downloads
2
Stars
1
Active Installs
5
Versions
Install in OpenClaw
/install a-stock
Description
🤖 OpenClaw Skill /skills | A股智投大师 | A股智能投研助手 | 行情分析 | 基本面分析 | 智能选股 | 自选股管理 | 监控预警 | AI Agent | 量化投资 | 金融科技 | FinTech
README (SKILL.md)

🛠️ 首次使用

需要配置 API Key

本技能依赖东方财富妙想数据,需要 API Key:

获取 API Key 方法

  1. 打开东方财富 APP
  2. 搜索「东方财富 skills」或「妙想
  3. 进入页面后点击「我的」→ 「API Key」
  4. 复制 Key

配置方式

配置到 mx-data、mx-search 等 skill 的环境变量中(参考各 skill 文档)。


A股智投大师 Skill

一个专注于A股市场的智能投研助手,整合东财数据、监控预警、智能选股等能力。

功能概览

模块 功能 Skills依赖
📊 行情分析 实时行情、资金流向、K线形态 mx-data
📈 基本面 PE/PB、ROE、财务报表、估值 mx-data
🎯 智能选股 按条件筛选股票 mx-select-stock
⭐ 自选股 查看/管理自选股 mx-selfselect
📰 舆情监控 新闻、研报、公告 mx-search
🔔 监控预警 成本百分比、均线金叉、RSI等 stock-monitor-skill

A股特色指标

A股特色指标 = {
    "涨停板": "连板数量、封板率、炸板率",
    "龙虎榜": "机构买入、游资动向",
    "融资融券": "融资余额、融券余量",
    "股东人数": "筹码集中度变化",
    "限售股解禁": "解禁时间表",
    "股权质押": "质押比例、预警线",
    "商誉减值": "商誉占净资产比",
    "ST/*ST": "风险警示、退市风险"
}

使用示例

1. 查询股票行情

用户:查一下贵州茅台现在多少钱
助手:调用 mx_data 查询 600519 最新价

2. 查看自选股

用户:我的自选股今天怎么样
助手:调用 mx_selfselect 查询自选股列表,然后批量查询每只股票的涨跌幅

3. 智能选股

用户:帮我选一下PE\x3C20的银行股
助手:调用 mx_select_stock 进行条件筛选

4. 深度分析

用户:分析一下宁德时代的投资价值
助手:
  1. 调用 mx_data 获取基本面数据
  2. 调用 mx_data 获取资金流向
  3. 调用 mx_search 获取最新新闻
  4. 综合分析给出建议

5. 设置监控

用户:帮我监控一下的成本价是50元
助手:调用 stock-monitor 添加监控规则

核心Prompt

你是一个专业的A股分析师,擅长:

1. 基于东财数据做基本面分析
   - PE/PB估值是否合理
   - 财务指标是否健康
   - 盈利能力和发展前景

2. 结合市场情绪和资金流向判断趋势
   - 主力资金是流入还是流出
   - 市场情绪是亢奋还是恐慌

3. 挖掘题材龙头和赛道机会
   - 所属题材是否有政策支持
   - 是否细分领域龙头

4. 识别A股特有的风险
   - ST/*ST风险
   - 限售股解禁
   - 股权质押比例
   - 商誉减值风险

分析原则:
- 用数据说话,别凭感觉
- 关注流动性和估值匹配
- 识别股东变化和资金动向
- 给出具体的买卖区间建议(仅供参考,不构成投资建议)

工作流程

用户请求
    ↓
┌─────────────────────────────┐
│  意图识别                   │
│  - 查行情                   │
│  - 看基本面                  │
│  - 选股票                   │
│  - 管理自选                  │
│  - 设置监控                  │
│  - 综合分析                  │
└─────────────────────────────┘
    ↓
┌─────────────────────────────┐
│  调用对应Skills              │
│  - mx_data                 │
│  - mx_selfselect           │
│  - mx_select_stock         │
│  - mx_search               │
│  - stock-monitor           │
└─────────────────────────────┘
    ↓
┌─────────────────────────────┐
│  数据整合与分析               │
│  - 格式化输出               │
│  - 对比分析                 │
│  - 风险提示                 │
│  - 投资建议                 │
└─────────────────────────────┘
    ↓
回复用户

注意事项

  1. 数据来源:所有数据来自东财API,仅供参考
  2. 投资风险:股市有风险,投资需谨慎
  3. API限制:东财API每天50次调用,注意使用频率
  4. 时效性:行情数据可能有延迟,请以实际交易为准

快速命令

命令 功能
查[股票] 查询股票行情
我的自选 查看自选股
选股条件 智能选股
分析[股票] 深度分析
监控[股票] 设置监控预警
Usage Guidance
This skill looks functionally coherent for A‑share analysis, but it requires an East Money (妙想/东财) API key even though the registry metadata does not declare required env vars — verify the source before providing credentials. Actionable steps: - Confirm the API endpoint (mkapi2.dfcfs.com/finskillshub/api/claw) is the official endpoint associated with the API key you obtain from the 东方财富 app. - Expect to set MX_API_KEY or MX_SEARCH_API_KEY (the code reads these); the skill will not prompt for them at install time according to metadata, so pay attention to SKILL.md instructions. - Review and understand the auto-install of dependent skills (mx-data, mx-search, mx-select-stock, mx-selfselect, stock-monitor-skill) — those skills may need the same API key or other credentials and will increase the attack surface. - If you don’t trust the publisher or the endpoint, do not enter your real API key; test in an isolated account or sandbox first, and monitor API usage/quota after enabling the skill. If the publisher can update the registry metadata to declare the required env vars (MX_API_KEY / MX_SEARCH_API_KEY) and confirm the endpoint, the inconsistency would be resolved and increase trust.
Capability Analysis
Type: OpenClaw Skill Name: a-stock Version: 1.1.0 The 'a-stock' skill is a legitimate A-share stock analysis tool that integrates with the East Money (dfcfs.com) Miaoxiang API. The code in 'a_stock_analysis.py' implements standard API interaction patterns for stock querying, screening, and news retrieval using an API key provided via environment variables. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions in 'SKILL.md' and 'README.md' are consistent with the stated purpose of providing financial analysis and stock monitoring.
Capability Assessment
Purpose & Capability
Name/description, README, SKILL.md and the Python code all align: this is an A‑share analysis skill that calls an East Money (妙想/东财) API and delegates tasks to mx-data, mx-search, mx-select-stock, mx-selfselect and stock-monitor-skill. No unrelated services or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to call the listed OpenClaw skills and to obtain/configure an East Money API key; runtime instructions do not ask the agent to read arbitrary local files or exfiltrate data beyond calls to the stated API endpoints and the other skills.
Install Mechanism
There is no install spec and only one included Python script. Nothing is downloaded or installed by the skill itself — lowest install risk for this package.
Credentials
The public registry metadata lists no required environment variables or primary credential, but both SKILL.md and scripts/a_stock_analysis.py require an East Money API key (looks for MX_API_KEY or MX_SEARCH_API_KEY) and instruct the user to configure it into related skills. This metadata mismatch (declared none vs. actual required API key) is an inconsistency that reduces transparency. Also note the code makes network POST requests to https://mkapi2.dfcfs.com/finskillshub/api/claw — confirm that endpoint is legitimate for the API key you provide.
Persistence & Privilege
always is false, no special privileges requested, and the skill does not attempt to modify other skills' configs or persist credentials itself. Autonomous invocation is enabled by default but not combined here with other high‑risk factors.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install a-stock
  3. After installation, invoke the skill by name or use /a-stock
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
重写代码,修复语法错误,移除中文emoji和标点
v1.0.4
- 更新描述,增加“OpenClaw Skill /skills”、“AI Agent”、“量化投资”、“金融科技”、“FinTech”等关键词,更全面覆盖相关金融科技场景 - 其余文档内容未改动,功能与依赖保持不变
v1.0.3
- 添加“OpenClaw专用”说明到描述字段,表明适配专用场景 - 其他功能说明、依赖和用法保持不变 - 文档调整提升技能定位清晰度,无功能变化
v1.0.2
新增详细README.md
v1.0.0
重命名为 a-stock
Metadata
Slug a-stock
Version 1.1.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 5
Frequently Asked Questions

What is A股智投大师?

🤖 OpenClaw Skill /skills | A股智投大师 | A股智能投研助手 | 行情分析 | 基本面分析 | 智能选股 | 自选股管理 | 监控预警 | AI Agent | 量化投资 | 金融科技 | FinTech. It is an AI Agent Skill for Claude Code / OpenClaw, with 645 downloads so far.

How do I install A股智投大师?

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

Is A股智投大师 free?

Yes, A股智投大师 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does A股智投大师 support?

A股智投大师 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created A股智投大师?

It is built and maintained by lucasxing1 (@lucasxing1); the current version is v1.1.0.

💬 Comments