← 返回 Skills 市场
Intelligent Stocks Screener
作者
Financial AI Analyst
· GitHub ↗
· v1.0.15
· MIT-0
24574
总下载
102
收藏
48
当前安装
16
版本数
在 OpenClaw 中安装
/install mx-stocks-screener
功能描述
基于东方财富数据库，支持通过自然语言输入筛选A港美股、基金、债券等多种资产，支持多元指标筛选，含技术面、消息面、基本面及市场情绪等，可用于全球资产速筛、跨市场监控、投资组合构建、策略回测等场景。返回结果包含数据说明及 csv 文件。Natural language screener for investment...
安全使用建议
Install only if you trust Eastmoney's service and have a revocable EM_API_KEY. Avoid putting confidential portfolio, client, or proprietary strategy details in queries, and set MX_STOCKS_SCREENER_OUTPUT_DIR if you need outputs confined to a specific folder.
能力评估
Purpose & Capability
The stated purpose, documentation, and script all align around natural-language screening for stocks, funds, ETFs, convertible bonds, and sectors, returning local CSV and description files.
Instruction Scope
The natural-language query scope is broad, but that is the core feature and execution is user-directed through required query and select-type parameters; no hidden trading, account mutation, or automatic invocation is shown.
Install Mechanism
The skill declares EM_API_KEY and installs the public Python package httpx. The dependency is unpinned, which is a reproducibility note rather than a security hold by itself.
Credentials
Use of EM_API_KEY and outbound requests to Eastmoney are disclosed and proportionate to the screener, but users should treat submitted queries as potentially sensitive investment research.
Persistence & Privilege
Persistence is limited to creating an output directory and writing CSV and text description files under the default or user-configured path; there is no background process, privilege escalation, deletion, broad indexing, or profile/session access.
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 mx-stocks-screener - 安装完成后，直接呼叫该 Skill 的名称或使用
/mx-stocks-screener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
v1.0.15
Publish 1.0.15
v1.0.14
- Added required environment variable declaration (EM_API_KEY) to metadata.
- No changes to code or user-facing features; documentation metadata improved for clarity and automation compatibility.
v1.0.13
- Removed "requires" (env, bins) section from metadata, making Python and environment variable checks external to the skill.
- No functional or interface changes; documentation and usage instructions remain unchanged.
v1.0.12
mx-stocks-screener 1.0.12
- 更新了环境变量配置说明，区分了 macOS 和 Linux 的不同 shell 启动文件（~/.zshrc 与 ~/.bashrc）。
- 相关步骤说明更详细，帮助用户根据操作系统正确加载环境变量。
- 其余功能、依赖、示例及接口保持不变。
v1.0.11
- Documentation cleanup: removed trailing whitespace and made minor formatting adjustments in SKILL.md.
- No functional changes to the code or features.
v1.0.10
- update display name
v1.0.9
- Minor description correction in SKILL.md ("A港美、基金、债券" updated to "A港美股、基金、债券")
- No user-facing feature or behavior change
v1.0.8
- Skill renamed from MX_StockPick (mx-stocks-screener) to mx_stocks_screener.
- Description updated to emphasize multi-asset, multi-market natural language screening, with an English summary added.
- Output file and directory naming conventions changed from MX_StockPick to mx_stocks_screener.
- Output directory environment variable renamed to MX_STOCKS_SCREENER_OUTPUT_DIR.
- Code and function examples updated to match new naming conventions (e.g., query_mx_stocks_screener).
- No code file changes detected; all updates pertain to documentation and usage guidance.
v1.0.7
Version 1.0.7 of mx-stockpick has no detected file or documentation changes from the previous version.
- No code or documentation updates in this release.
- Functionality and usage remain unchanged.
- rename to Intelligent Stock Screener
v1.0.6
Version 1.0.6
- No file changes detected in this release.
- No updates to user-facing features, functionality, or documentation.
- Rename to Intelligent Stocks Screene
v1.0.5
MX_StockPick 1.0.5 Changelog
- 依赖由 httpx pandas 精简为仅 httpx，安装更简便。
- 增加密钥安全和使用说明，强调 EM_API_KEY 来源及防止密钥泄露。
- 更新默认输出目录为 miaoxiang/MX_StockPick。
- 强化筛选能力，明确支持复合逻辑、技术面、消息面、情绪等多类别条件组合。
- 优化命令行和代码调用示例，并调整输出文件命名方式（基于查询ID）。
- 文档更加聚焦东方财富妙想的功能场景和数据合规性说明。
v1.0.4
-fix pypinyin error
v1.0.3
- 移除了对 pypinyin 的依赖，仅需安装 httpx 和 pandas。
- 安装依赖示例和相关说明已同步更新。
- Python 代码调用示例中，函数名由 query_select_stock 更改为 query_MX_StockPick。
v1.0.2
统一命名规范：将技能标识（slug）中的连字符 `-` 替换为下划线 `_`
v1.0.1
- 文档优化：所有相关说明、环境变量和注册说明同步修改为“妙想”
- 无功能及代码更改
v1.0.0
- Initial release of MX_StockPick.
- Enables natural language stock, sector, and fund selection for A-shares, HK stocks, US stocks, funds, ETFs, convertible bonds, and sectors.
- Integrates with MiaoXiang intelligent stock-picking tool to fetch and output full CSV data and a data description file.
- Supports filtering by financial/market indicators, technical signals, business info, industry/sector, and more.
- Advanced queries available for A-shares, including executive, shareholder, and dividend info.
- Requires EM_API_KEY environment variable setup and Python dependencies (httpx, pandas, pypinyin).
元数据
常见问题
Intelligent Stocks Screener 是什么？
基于东方财富数据库，支持通过自然语言输入筛选A港美股、基金、债券等多种资产，支持多元指标筛选，含技术面、消息面、基本面及市场情绪等，可用于全球资产速筛、跨市场监控、投资组合构建、策略回测等场景。返回结果包含数据说明及 csv 文件。Natural language screener for investment... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 24574 次。
如何安装 Intelligent Stocks Screener？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mx-stocks-screener」即可一键安装，无需额外配置。
Intelligent Stocks Screener 是免费的吗？
是的，Intelligent Stocks Screener 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Intelligent Stocks Screener 支持哪些平台？
Intelligent Stocks Screener 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 Intelligent Stocks Screener？
由 Financial AI Analyst（@financial-ai-analyst）开发并维护，当前版本 v1.0.15。
推荐 Skills