← Back to Skills Marketplace
hongjiaping2010-coder

A股分析技能包装器

by Xiaoxiaofu · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
297
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install akshare-wrapper
Description
A股分析技能包装器,基于akshare数据源。支持实时行情、个股分析、板块轮动、资金流向等A股分析功能。使用自然语言查询A股市场数据。
README (SKILL.md)

A股分析技能 (akshare-wrapper)

功能特性

  • 实时大盘行情:上证、深证、创业板、沪深300等主要指数
  • 个股K线分析:历史K线数据,支持日线、周线、月线
  • 资金流向监控:个股、板块、市场资金流向分析
  • 板块轮动分析:行业板块、概念板块涨跌排行
  • 涨跌停统计:涨停池、跌停池、连板梯队
  • 基本面分析:财务指标、财报数据、融资融券
  • 港股/美股:跨市场行情数据
  • 新闻研报:财经新闻、机构研报

使用示例

大盘行情

  • "A股大盘" - 查看实时指数行情
  • "上证指数" - 上证指数实时数据
  • "创业板指" - 创业板指数行情

个股分析

  • "贵州茅台近30日K线" - 查看个股历史走势
  • "茅台资金流向" - 查看个股资金流向
  • "茅台怎么样" - 个股综合信息
  • "600519周线" - 使用股票代码查询

板块分析

  • "行业板块涨跌" - 行业板块表现排行
  • "概念板块涨跌" - 概念板块表现排行
  • "板块资金流向" - 板块资金净流入排行

市场统计

  • "今日涨停" - 涨停跌停统计
  • "连板梯队" - 连板股统计
  • "炸板率" - 涨停炸板情况

其他功能

  • "港股行情" - 港股市场行情
  • "美股行情" - 美股市场行情
  • "财经新闻" - 最新财经新闻
  • "推荐股票" - 股票推荐

技术依赖

Python包

pip install akshare pandas numpy

版本要求

  • akshare>=1.18.0
  • pandas>=3.0.0
  • numpy>=2.4.0

快速开始

命令行使用

cd /root/.openclaw/workspace/skills/akshare-wrapper
python3 main.py "A股大盘"

OpenClaw集成

技能安装后,可在OpenClaw中直接使用自然语言查询:

  • "帮我看看A股大盘"
  • "茅台最近走势怎么样"
  • "今天哪个板块最强"

输出格式

技能输出针对聊天平台优化:

  • 使用emoji增强可读性
  • 关键数据突出显示
  • 分段清晰,避免信息过载
  • 包含数据更新时间戳

性能特点

  • 快速响应:大部分查询2-3秒内返回
  • 智能缓存:重复查询使用缓存提高速度
  • 错误处理:网络异常友好提示
  • 超时控制:长查询自动超时保护

注意事项

数据源

  • 数据来自akshare,最终源为新浪财经、东方财富等
  • 数据有延迟,非实时Level2数据
  • 港股/美股查询可能较慢

使用限制

  • 避免短时间内高频查询
  • 复杂查询可能需要更长时间
  • 非交易时间数据可能不更新

故障处理

  1. 查询无响应:检查网络连接,确认akshare安装
  2. 导入错误:确认python依赖已安装
  3. 数据不更新:检查数据源状态,确认交易时间

高级功能

持仓管理

支持简单的持仓管理功能:

  • "我的持仓" - 显示当前持仓
  • "添加持仓 600519 --cost 10.5 --qty 1000" - 添加持仓
  • "持仓分析" - 分析持仓盈亏

股票筛选

基于当前市场情况的股票推荐:

  • "推荐股票" - 综合推荐
  • "半导体股票推荐" - 板块内推荐

更新日志

v1.0 (2026-03-11)

  • 初始版本发布
  • 基于akshare-stock技能包装
  • 修复导入问题
  • 添加统一错误处理
  • 优化输出格式

技术支持

问题反馈

如遇问题,请提供:

  1. 查询的具体内容
  2. 错误信息(如有)
  3. 期望的输出

功能建议

欢迎提出新功能建议,包括:

  1. 需要新增的数据类型
  2. 输出格式改进
  3. 性能优化建议

许可证

基于akshare-stock技能,遵循原技能许可证。


技能状态: ✅ 可用
最后测试: 2026-03-11
维护团队: 小富AI助手
推荐用途: A股市场分析、投资研究、团队协作

Usage Guidance
This wrapper delegates all work to /root/.openclaw/skills/akshare-stock/main.py. Before installing or enabling it: 1) Verify that the akshare-stock skill actually exists at that path and inspect its code — the wrapper will run that script as-is and its behavior determines what runs on your system. 2) Ensure the underlying skill and any third-party Python packages (akshare, pandas, numpy) are trustworthy and at compatible versions. 3) The wrapper uses subprocess.run with a safe argument list (no shell), which reduces injection risk, but delegation to an undeclared path is the main concern. If you cannot audit the akshare-stock skill, treat this as potentially risky and avoid installing.
Capability Analysis
Type: OpenClaw Skill Name: akshare-wrapper Version: 1.0.0 The skill bundle is a functional wrapper for the 'akshare' financial data library, designed to provide A-share market analysis via an underlying 'akshare-stock' skill. The main.py script safely delegates natural language queries using subprocess.run with argument lists, avoiding shell injection vulnerabilities. The SKILL.md documentation provides clear instructions for the AI agent and includes standard financial analysis features without any evidence of malicious intent, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The skill is described as an akshare-based A-share analysis wrapper and declares Python deps (akshare, pandas, numpy) which is coherent. However, the bundled main.py does not implement data fetching itself — it delegates to a different skill path (/root/.openclaw/skills/akshare-stock). That implicit dependency on another skill is not declared in SKILL.md or metadata and is surprising.
Instruction Scope
Runtime instructions and main.py are narrowly scoped: they preprocess user query and run a subprocess to invoke another skill's main.py. The wrapper does not read environment variables or other system files. The concern is delegation: it runs code from /root/.openclaw/skills/akshare-stock; the wrapper's behavior and outputs therefore depend entirely on that target script (which could do anything).
Install Mechanism
No install step (instruction-only plus a small main.py). This has low installation risk because nothing is downloaded or extracted during install.
Credentials
The skill does not request environment variables, credentials, or config paths. The declared Python package requirements are proportional to the stated purpose.
Persistence & Privilege
always:false and no special persistence or modifications to other skills' configs. The skill can be invoked autonomously by the agent (platform default), but that is not combined with additional privileges here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install akshare-wrapper
  3. After installation, invoke the skill by name or use /akshare-wrapper
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
akshare-wrapper v1.0.0 - 首次发布,提供A股分析技能包装器,基于akshare数据源 - 支持实时行情、个股K线、资金流向、板块轮动、市场统计等多项A股分析功能 - 优化自然语言查询体验,适配OpenClaw平台 - 增强错误处理和输出格式,提升聊天平台可读性 - 集成持仓管理和基于市场情况的股票推荐功能
Metadata
Slug akshare-wrapper
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is A股分析技能包装器?

A股分析技能包装器,基于akshare数据源。支持实时行情、个股分析、板块轮动、资金流向等A股分析功能。使用自然语言查询A股市场数据。 It is an AI Agent Skill for Claude Code / OpenClaw, with 297 downloads so far.

How do I install A股分析技能包装器?

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

Is A股分析技能包装器 free?

Yes, A股分析技能包装器 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does A股分析技能包装器 support?

A股分析技能包装器 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created A股分析技能包装器?

It is built and maintained by Xiaoxiaofu (@hongjiaping2010-coder); the current version is v1.0.0.

💬 Comments