← 返回 Skills 市场
zhaohaixin

A Stock Analyst.Bak

作者 POC · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
123
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install a-stock-analyst-bak
功能描述
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
使用说明 (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
安全使用建议
What to check before installing: - Verify the data endpoint: the script posts to https://mkapi2.dfcfs.com/finskillshub/api/claw. Confirm that this domain is the legitimate Eastmoney/妙想 API you expect before providing an API key. - API key handling: the code expects MX_API_KEY or MX_SEARCH_API_KEY but the skill metadata declares no required env vars. Ask the publisher to explicitly list required env vars and where the key will be stored/used. Treat the API key as sensitive: only provide it if you trust the endpoint and the skill's origin. - Provenance mismatch: _meta.json ownerId differs from the registry owner id and version numbers differ; this may indicate the package was repackaged. Prefer skills with clear, verifiable authorship. - Auto-install of other skills: SKILL.md asks the agent to auto-install related skills (mx-data, mx-search, etc.). Review those skills' manifests and permissions before allowing automatic installs; they may also require credentials. - Minimize risk: if you test, do so in a sandboxed account with a limited or read-only API key and monitor network traffic. If unsure, request the publisher to correct the manifest (declare required env vars and owner) or obtain the code from a verified source. Confidence note: medium — behavior aligns with a legitimate stock-data integration, but the undeclared credential usage and provenance discrepancies are unresolved and justify caution.
功能分析
Type: OpenClaw Skill Name: a-stock-analyst-bak Version: 1.0.0 The skill bundle is a legitimate stock analysis tool for the A-share market, designed to interface with East Money's (dfcfs.com) 'Miao Xiang' API. The Python script (scripts/a_stock_analysis.py) implements standard API request logic to fetch market data, news, and manage watchlists using a user-provided API key. The documentation (SKILL.md) provides clear instructions for the AI agent to act as a financial analyst without any signs of prompt injection or malicious intent.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill's name/description (A股分析) matches its behavior: it queries a market-data API, performs screening, self-select management and news search. Requesting an Eastmoney-style API key is coherent. However, the package metadata does not declare any required env vars while the code expects MX_API_KEY or MX_SEARCH_API_KEY — an internal documentation/manifest mismatch.
Instruction Scope
SKILL.md confines runtime actions to calling other skills (mx-data, mx-search, etc.) and Eastmoney/妙想 API for data. It does not instruct reading arbitrary system files or sending data to unexpected endpoints beyond the stated data provider.
Install Mechanism
There is no install spec (instruction-only plus included Python script). No downloads from external URLs or archive extraction are requested. The only executable code is a contained Python script that makes network requests.
Credentials
The code reads MX_API_KEY / MX_SEARCH_API_KEY from the environment and sends it as an 'apikey' header to https://mkapi2.dfcfs.com/finskillshub/api/claw. The skill manifest lists no required env vars, yet SKILL.md instructs the user to configure an API Key into other skills. This mismatch (undeclared credential usage + transmitting the key to an external host) is disproportionate to what the manifest advertises and should be clarified.
Persistence & Privilege
The skill does not request always:true, does not modify other skills' configs, and does not claim system-wide persistence. It can be invoked autonomously (platform default) but that alone is not flagged.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install a-stock-analyst-bak
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /a-stock-analyst-bak 触发
  4. 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
v1.0.0
a-stock-analyst-bak v1.0.0 - 首发版本,发布“A股智投大师”智能投研助手。 - 支持A股行情分析、基本面分析、智能选股、自选股管理、监控预警等功能。 - 集成东方财富数据,依赖多个配套技能(mx-data、mx-search、mx-select-stock、mx-selfselect、stock-monitor-skill)。 - 提供详细API Key配置说明与常见A股特色指标支持。 - 包含标准工作流程、核心分析Prompt及常用命令指南。
元数据
Slug a-stock-analyst-bak
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

A Stock Analyst.Bak 是什么?

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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 123 次。

如何安装 A Stock Analyst.Bak?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install a-stock-analyst-bak」即可一键安装,无需额外配置。

A Stock Analyst.Bak 是免费的吗?

是的,A Stock Analyst.Bak 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

A Stock Analyst.Bak 支持哪些平台?

A Stock Analyst.Bak 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 A Stock Analyst.Bak?

由 POC(@zhaohaixin)开发并维护,当前版本 v1.0.0。

💬 留言讨论