← Back to Skills Marketplace
349
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install a-stock-analyzer
Description
A股智能分析交易助手（专业版）。基于马克·米勒维尼趋势模板和7大严格财务条件筛选优质个股，适用于追求高基本面标准的价值趋势投资者。
README (SKILL.md)
A股智能分析交易助手（专业版）
概述
本技能采用7大严格选股条件，结合技术面和基本面，筛选A股市场中最优质的个股。
7大选股条件
| 条件 | 说明 |
|---|---|
| 1 | 剔除ST股票和上市不满1年的次新股 |
| 2 | 最近一季度营业收入同比增长率 > 25% |
| 3 | 最近一季度净利润同比增长率 > 30% 且环比增长为正 |
| 4 | 股价处于30日均线上方或接近均线（5%以内） |
| 5 | 最近10个交易日平均成交量 > 120日均量（放量） |
| 6 | 净资产收益率（ROE）> 15% |
| 7 | 最近三年净利润复合增长率 > 20% |
核心功能
1. 大盘分析
- 上证指数、深证成指、创业板指、科创板指
- 实时涨跌幅
2. 专业选股
- 从热门股票池筛选
- 逐个检查7大条件
- 获取K线数据计算技术指标
- 获取财务数据分析基本面
3. 买卖建议
- 买入区间（现价±2%）
- 目标价（+15%）
- 止损价（-5%）
- 仓位配置（60%/20%/20%）
使用方式
手动触发
# 完整分析（大盘+选股）
python3 scripts/analyze.py --full
# 只看大盘
python3 scripts/analyze.py --market
# 只选股
python3 scripts/analyze.py --stocks
自动推送
配置 cron 定时任务：
# 每天早上8点分析
0 8 * * 1-5 cd /path/to/a-stock-analyzer && python3 scripts/analyze.py --full
配置文件 (config.json)
{
"push": {
"enabled": true,
"times": ["08:00", "14:00"],
"channels": ["dingtalk"]
},
"stock": {
"max_holdings": 3,
"recommend_count": 3,
"position_ratio": [0.6, 0.2, 0.2]
},
"risk": {
"stop_loss_pct": 5,
"stop_profit_pct": 15,
"max_position_pct": 60
}
}
技术指标
| 指标 | 说明 |
|---|---|
| MA30 | 30日均线，价格支撑/压力位 |
| MA60 | 60日均线，中期趋势 |
| MA120 | 120日均线，长期趋势 |
| VOL_MA10 | 10日均量，短期成交量 |
| VOL_MA120 | 120日均量，长期均量 |
财务指标
| 指标 | 说明 | 筛选标准 |
|---|---|---|
| 营收同比 | 营业收入增长速率 | > 25% |
| 净利润同比 | 净利润增长速率 | > 30% |
| 净利润环比 | 净利润环比增长 | > 0% |
| ROE | 净资产收益率 | > 15% |
| 三年复合增长率 | 净利润3年CAGR | > 20% |
输出文件
reports/report_YYYYMMDD_HHMMSS.md- 每日分析报告
风险提示
⚠️
- 本技能仅供参考，不构成投资建议
- 股市有风险，入市需谨慎
- 请根据自身风险承受能力使用
- 严格执行止损纪律
依赖安装
pip install akshare pandas numpy requests
更新日志
- v2.0.0: 专业版，支持7大严格选股条件，马克·米勒维尼趋势模板
- v1.0.0: 初始版本，基础选股功能
Usage Guidance
This skill appears to do what it claims (market data fetch → analysis → report → optional webhook push). Before installing or running: 1) Review and set the webhook URLs in config.json (feishu_webhook / dingtalk_webhook) — leaving them blank means no push. 2) Run in a restricted environment (non‑root, isolated directory) because it performs network I/O to public APIs and will write caches/reports to disk. 3) If you plan to enable automated cron runs, verify the cron command works and that the skill's network access is acceptable. 4) Expect some bugs (inconsistent report scores, and SKILL.md/config mismatch) — inspect logs/reports during initial runs. 5) Do not store sensitive credentials in config.json; the skill does not request them but any webhook you provide will receive the report content.
Capability Analysis
Type: OpenClaw Skill
Name: a-stock-analyzer
Version: 2.2.0
The skill bundle is a legitimate stock analysis tool for the Chinese A-share market, implementing technical and financial screening based on the Mark Minervini trend template. The code in `scripts/analyze.py` and `scripts/pusher.py` fetches data from public financial APIs (Tencent, EastMoney, and akshare) and generates Markdown reports. While it includes functionality to push notifications to Feishu or DingTalk via webhooks, this is a documented feature controlled by the user's `config.json` and shows no signs of malicious exfiltration or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description match the code and files: scripts fetch market data (EastMoney/Tencent/akshare), compute indicators, generate reports and optionally push to Feishu/DingTalk. No unrelated credentials, binaries, or platform access are requested.
Instruction Scope
Runtime instructions and scripts stay within the stated purpose (fetch market data, analyze, write reports, push to webhooks). Minor inconsistencies: SKILL.md example config shows 'channels': ['dingtalk'] while the included config.json uses 'feishu' and an empty feishu_webhook. Reports in the repository contain inconsistent/contradictory risk scores (e.g. 100 then 0) which looks like a logic/reporting bug rather than malicious behavior. The scripts read and write only local files under the skill directory (config.json, cache, reports, logs) and send network requests to public market APIs and webhook endpoints — this is expected for this skill but worth noting.
Install Mechanism
No install spec; SKILL.md lists Python and pip packages (akshare, pandas, numpy, requests). Dependencies are proportional to the task. No downloads from untrusted URLs or archive extraction are present in the package.
Credentials
The skill requests no environment variables or secrets. Push webhooks are read from config.json (local file), which is reasonable for a push feature; there are no requests for unrelated service keys or system credentials.
Persistence & Privilege
Skill is not always-enabled and uses normal autonomous invocation defaults. It does not attempt to modify other skills or system-wide agent configuration. It writes report/cache files only under its own directory.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install a-stock-analyzer - After installation, invoke the skill by name or use
/a-stock-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.0
- Added scripts/pusher.py for push notification functionality.
- New automated daily analysis reports are now generated in the reports/ directory.
- Updated analyze.py and config.json to support push features and enhanced reporting.
- Minor updates to financial data caching.
v2.1.0
a-stock-analyzer 2.1.0
- 增加详细文档，系统介绍7大严格选股条件，与马克·米勒维尼趋势模板结合
- 明确支持大盘分析、专业选股、买卖建议等模块，详细说明用法和输出
- 提供标准化配置文件说明及参数说明
- 补充关键技术和财务指标参考，标准化筛选和买卖规则
- 添加风险提示和依赖安装说明，方便用户快速上手
Metadata
Frequently Asked Questions
What is A Stock Analyzer?
A股智能分析交易助手（专业版）。基于马克·米勒维尼趋势模板和7大严格财务条件筛选优质个股，适用于追求高基本面标准的价值趋势投资者。 It is an AI Agent Skill for Claude Code / OpenClaw, with 349 downloads so far.
How do I install A Stock Analyzer?
Run "/install a-stock-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is A Stock Analyzer free?
Yes, A Stock Analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does A Stock Analyzer support?
A Stock Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created A Stock Analyzer?
It is built and maintained by dxihyv (@dxihyv); the current version is v2.2.0.
More Skills