功能描述

基于AKShare实时数据，智能评分和动态权重调整，提供多市场多维度股票选股与风险控制建议。

使用说明 (SKILL.md)

AKShare集成选股技能

Name: Akshare Integrated
Author: haosongyi-star

基于AKShare实时数据的智能选股技能，集成动态权重调整和行业差异化评分。

🎯 技能特性

实时数据：集成AKShare获取实时股价
智能评分：三层九维评分系统
动态权重：根据市场趋势调整权重
行业差异化：不同行业不同评分标准
风险控制：完善的风控与失效体系
证据分层：A/B/C/D四级证据体系

📦 安装要求

# 安装AKShare
pip install akshare --upgrade

# 安装依赖
pip install pandas numpy

🚀 使用方法

基本选股

# 运行选股分析
stock-selector-akshare run

# 使用特定市场
stock-selector-akshare run --market hk

# 指定股票代码
stock-selector-akshare run --symbols 00700,00998,01810

获取实时数据

# 获取港股实时数据
stock-selector-akshare data hk 00700

# 获取A股实时数据
stock-selector-akshare data a 000001

# 获取美股实时数据
stock-selector-akshare data us AAPL

批量查询

# 批量查询港股
stock-selector-akshare batch hk 00700,00998,01810

# 多市场查询
stock-selector-akshare multi "00700,000001,AAPL"

🔧 系统架构

1. 数据层

AKShare接口：获取实时股票数据
数据缓存：5分钟本地缓存
错误处理：多数据源备选机制

2. 评分层

价值层 (40%)：基本面、行业位势、估值赔率
交易层 (35%)：资金结构、价格形态、量价配合
风险层 (25%)：波动风险、事件风险、流动性风险

3. 决策层

动作决策：BUY/HOLD/REDUCE/SELL/WATCH
仓位建议：基于评分和风险评估
触发条件：量化的买入/卖出触发点

4. 风控层

风险边界：明确的止损/止盈点
失效条件：系统失效的识别标准
证据分级：A/B/C/D四级证据可靠性

📊 评分系统

价值层 (40分)

基本面质量 (15分)
- 财务健康度
- 盈利能力
- 成长前景
行业位势 (15分)
- 行业地位
- 竞争格局
- 政策支持
估值赔率 (10分)
- PE/PB/PS估值
- 历史估值分位数
- 相对估值优势

交易层 (35分)

资金结构 (10分)
- 主力资金流向
- 外资持股比例
- 机构调研热度
裸K形态 (10分)
- 关键价位突破
- 技术形态形成
- 趋势强度
量价配合 (15分)
- 成交量放大
- 价格有效性
- 突破确认

风险层 (25分)

波动风险 (10分)
- 历史波动率
- 日内波动幅度
- Beta系数
事件风险 (10分)
- 重要事件临近
- 政策风险
- 行业风险
流动性风险 (5分)
- 成交量稳定性
- 买卖价差
- 市场深度

🎯 决策规则

动作决策

条件	动作
总分 ≥ 85，价值层均衡，形态分 ≥ 8	BUY
总分 ≥ 70，交易层均衡	HOLD
总分 \x3C 70，风险层亮红灯	REDUCE
总分 \x3C 60，且发生风险事件	SELL
其他情况	WATCH

仓位建议

评分区间	建议仓位	理由
≥ 90	15%	优秀标的，确定性高
85-89	10%	良好标的，机会明确
80-84	8%	机会标的，适度配置
70-79	5%	观察标的，谨慎配置

⚠️ 风险控制

风险边界

止损线：-8% ~ -12%
止盈线：+20% ~ +30%
最大仓位：单只股票 ≤ 15%
总仓位：激进市场 ≤ 80%，保守市场 ≤ 50%

失效条件

系统失效：连续3次数据获取失败
策略失效：连续5次推荐亏损
市场失效：大盘单日跌幅 > 5%
流动性失效：成交量萎缩 > 50%

🔍 使用示例

示例1：分析腾讯控股

stock-selector-akshare run --symbols 00700 --format json

输出:

{
  "success": true,
  "timestamp": "2026-03-11T04:15:30Z",
  "results": [
    {
      "symbol": "00700",
      "name": "腾讯控股",
      "action": "BUY",
      "total_score": 94,
      "position_suggestion": "7%",
      "real_time_price": 562.500,
      "change_percent": "+0.45%",
      "recommendation": "强烈推荐买入",
      "evidence_level": "A"
    }
  ]
}

示例2：批量分析港股

stock-selector-akshare batch hk 00700,00998,01810

示例3：多市场分析

stock-selector-akshare multi "00700,000001,AAPL"

🔄 集成方式

Python集成

from stock_selector_akshare import AKShareStockSelector

# 创建选择器
selector = AKShareStockSelector()

# 分析单只股票
result = selector.analyze_stock("00700", market="hk")

# 批量分析
results = selector.analyze_batch(["00700", "00998"], market="hk")

# 获取实时数据
real_time_data = selector.get_real_time_data("00700", "hk")

API集成

# 获取实时数据API
curl "http://localhost:8080/api/stock/00700?market=hk"

# 批量分析API
curl -X POST "http://localhost:8080/api/analyze/batch" \
  -H "Content-Type: application/json" \
  -d '{"symbols":["00700","00998"],"market":"hk"}'

🚨 注意事项

数据延迟：免费接口可能有15-30秒延迟
交易时间：非交易时间返回的数据可能是0
频率限制：避免频繁调用，建议1秒以上间隔
缓存策略：默认5分钟缓存，减少API调用
错误处理：添加重试机制和备用数据源

📈 性能优化建议

批量获取：使用全市场数据API，避免单只股票多次调用
缓存策略：本地缓存 + 内存缓存组合
异步处理：使用异步请求提高并发性能
连接复用：保持HTTP连接复用
数据压缩：启用数据压缩减少传输量

🔧 维护说明

日常维护

检查AKShare库更新
测试数据获取接口
验证评分算法有效性

故障排查

检查网络连接
验证AKShare安装
查看错误日志
测试备用数据源

性能监控

API响应时间
数据获取成功率
评分计算耗时
内存使用情况

技能状态：🚀 已集成AKShare
版本：v2.0
最后更新：2026-03-11
维护者：OpenClaw技能库

安全使用建议

This SKILL.md describes a useful AKShare-based stock selector but is missing the actual CLI/package/server that the examples call (stock-selector-akshare and stock_selector_akshare). Before installing or running anything: 1) Ask the publisher for the authoritative source (PyPI package name, GitHub repo, or published binary) that provides the CLI/module and the service API; 2) verify the source code or release artifact and its integrity (review repository, maintainers, and recent commits); 3) avoid blindly running 'pip install' in a production environment—install in an isolated environment (virtualenv/container) and inspect dependencies; 4) if you must run a local API server, ensure it’s from a trusted repository and run with least privilege and network restrictions; 5) confirm licensing, data sources, and rate limits for AKShare usage. The main issue here is incoherence (missing runtime artifacts), not explicit malicious behavior, but that gap increases risk if you search for and install third-party code to fill it.

功能分析

Type: OpenClaw Skill Name: akshare-integrated Version: 1.0.0 The skill bundle provides documentation and metadata for a stock analysis tool integrated with the AKShare financial data library. The SKILL.md file outlines a comprehensive scoring system, risk control parameters, and usage examples for market analysis without any evidence of malicious intent, data exfiltration, or prompt injection attacks.

能力评估

ℹ Purpose & Capability

The skill claims to integrate AKShare for real-time stock selection, and the declared dependencies (akshare, pandas, numpy) are consistent with that purpose. However, the SKILL.md repeatedly references a CLI 'stock-selector-akshare' and a Python module 'stock_selector_akshare' (and an HTTP API at localhost) that are not included, published, or installed by the instructions—there is no install spec or package name that would provide those artifacts. That mismatch means a user following the instructions will not get the advertised CLI/module unless they obtain additional code from elsewhere.

ℹ Instruction Scope

Instructions focus on fetching data via AKShare and computing scores, which is within scope. They do not request unrelated files or secrets. Concern: instructions assume running a local service and a CLI/module without giving installation/source for that service, and leave implementation details vague (caching, backup sources, API endpoints). This ambiguity could lead the operator to install third-party code from unknown sources.

ℹ Install Mechanism

There is no formal install spec in the skill bundle; SKILL.md suggests 'pip install akshare pandas numpy'. Installing packages from PyPI is typical but executes code from external registries—expected for this purpose but still a security consideration. Importantly, the SKILL.md does not provide any package or repository for the 'stock-selector-akshare' CLI or the 'stock_selector_akshare' Python module, so the bundle itself supplies no runtime artifacts.

✓ Credentials

The skill requests no environment variables, credentials, or config paths. Nothing in the documentation asks for unrelated secrets. This is proportionate to the stated purpose.

✓ Persistence & Privilege

The skill does not request 'always: true', does not include install-time scripts in the bundle, and does not declare modifying other skill or system configuration. It requires no persistent privileges within the agent manifest.

版本历史

v1.0.0

- 首发版本，集成 AKShare 实时数据与多市场股票分析能力 - 提供三层九维智能评分系统和动态权重调整 - 支持多行业差异化评分与 A/B/C/D 四级证据体系 - 实现完善风险控制和失效判定机制 - 提供命令行、Python、API 多种接口及批量处理能力

元数据

Slug akshare-integrated

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

Akshare Integrated 是什么？

基于AKShare实时数据，智能评分和动态权重调整，提供多市场多维度股票选股与风险控制建议。它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 410 次。

如何安装 Akshare Integrated？

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

Akshare Integrated 是免费的吗？

是的，Akshare Integrated 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Akshare Integrated 支持哪些平台？

Akshare Integrated 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 Akshare Integrated？

由 haosongyi-star（@haosongyi-star）开发并维护，当前版本 v1.0.0。

Akshare Integrated