← Back to Skills Marketplace
Stock Screener
by
weqwhdiowa
· GitHub ↗
· v1.0.0
· MIT-0
568
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install china-stock-screener
Description
基于技术面、资金面、基本面三维度筛选A股和港股符合条件的股票。支持多因子选股、条件过滤、排序输出。
README (SKILL.md)
Stock Screener - 智能选股器
功能概述
根据用户指定的条件,从A股(上海/深圳交易所)和港股(港交所)中筛选符合条件的股票。
使用场景
- 当用户提及"选股"、"筛选股票"、"条件选股"时使用
- 支持技术面选股(均线、MACD、KDJ等)
- 支持资金面选股(主力净流入、北向/南向资金)
- 支持基本面选股(PE、PB、ROE、股息率等)
- 支持多条件组合筛选
筛选维度
1. 技术面指标
| 指标 | 参数 | 说明 |
|---|---|---|
| 均线多头排列 | MA5>MA10>MA20>MA60 | 上升趋势 |
| MACD金叉 | DIF上穿DEA | 买入信号 |
| KDJ金叉 | K上穿D | 超卖反弹 |
| 放量上涨 | 成交量>均量1.5倍 | 量价配合 |
| 突破新高 | 收盘价创N日新高 | 强势信号 |
| 站上年线 | 收盘价>MA250 | 长期趋势转强 |
2. 资金面指标
| 指标 | 参数 | 说明 |
|---|---|---|
| 主力净流入 | 今日主力净流入>0 | 资金推动 |
| 北向资金买入 | 近N日北向净买入 | 外资看好 |
| 南向资金买入 | 近N日南向净买入 | 内资看好港股 |
| 融资余额增加 | 融资余额增长>X% | 杠杆资金入场 |
| 大单买入比 | 大单买入>60% | 机构信号 |
3. 基本面指标
| 指标 | 参数 | 说明 |
|---|---|---|
| PE估值 | PE\x3CXX 或 PE在历史分位\x3CXX% | 估值筛选 |
| PB估值 | PB\x3CXX | 资产筛选 |
| ROE | ROE>XX% | 盈利能力 |
| 股息率 | 股息率>XX% | 高股息 |
| 净利润增速 | 净利润同比增长>XX% | 成长性 |
| 营收增速 | 营收同比增长>XX% | 成长性 |
4. 市场与行业
| 指标 | 参数 |
|---|---|
| 上市市场 | 沪市A股/深市A股/创业板/科创板/港股主板/港股通 |
| 行业板块 | 银行/新能源/医药/消费/科技等 |
| 市值范围 | 小盘/中盘/大盘/超大盘 |
| 日成交额 | >XX亿 |
预设筛选模板
模板1:强势股筛选
- 均线多头排列
- MACD金叉
- 放量上涨(量比>1.5)
- 主力净流入>0
- 近5日涨幅>0
模板2:低估价值股筛选
- PE\x3C15 且 PE历史分位\x3C30%
- 股息率>3%
- ROE>10%
- 净利润正增长
模板3:北向资金青睐股
- 北向资金连续净买入>3日
- 北向资金持仓增长>5%
- PE\x3C30
- 日成交额>5亿
模板4:港股通低估筛选
- 南向资金连续净买入>5日
- PE\x3C10
- 股息率>4%
- AH溢价>20%
模板5:高成长股筛选
- 净利润增速>30%
- 营收增速>20%
- ROE>15%
- PEG\x3C1
使用方法
基础筛选
直接告诉筛选条件,例如:
- "筛选PE\x3C20的银行股"
- "帮我找MACD金叉的科技股"
- "北向资金连续买入的股票"
组合筛选
指定多个条件:
- "帮我筛选同时满足:PE\x3C20、股息率>3%、ROE>15%的股票"
使用预设模板
- "用强势股模板筛选"
- "用低估价值股模板帮我选股"
输出格式
筛选结果
## 筛选结果
共筛选出 X 只符合条件的股票:
| 排名 | 代码 | 名称 | 现价 | 涨跌幅 | 评分 | 筛选理由 |
|------|------|------|------|--------|------|----------|
| 1 | 600036 | 招商银行 | 39.50 | +1.02% | 85 | 低估+高股息+北向买入 |
| 2 | ... | ... | ... | ... | ... | ... |
每只股票详情
### 600036 招商银行
**综合评分**: 85/100
| 维度 | 得分 | 详情 |
|------|------|------|
| 技术面 | 28/30 | 均线多头排列,MACD金叉 |
| 资金面 | 30/35 | 北向资金净买入,融资余额增长 |
| 基本面 | 27/35 | PE=7x,ROE=15%,股息率4.7% |
**筛选匹配**:
- ✅ PE\x3C15
- ✅ 股息率>3%
- ✅ ROE>10%
- ✅ 北向资金净买入
数据来源
- A股数据:东方财富、同花顺
- 港股数据:东方财富、同花顺
- 资金流向:东方财富
- 财务数据:年报/季报
注意事项
- 筛选结果仅供参考,不构成投资建议
- 港股筛选支持港股通标的
- 筛选结果按综合评分排序
- 建议结合行业配置分散风险
Usage Guidance
This skill is an instruction-only stock screener and appears coherent. Before installing, consider: (1) it names data sources (东方财富、同花顺) but provides no API endpoints or keys — confirm how your agent will obtain market and fund‑flow data (web access, licensed APIs, or platform connectors); (2) if the agent is allowed to browse the web or scrape those sites, verify that such access is permitted and that scraping won't leak other sensitive data; (3) the skill is informational and explicitly not investment advice — treat outputs as suggestions and verify with trusted data; (4) if you expect automated live screening, you may need to provide or configure official data APIs or credentials separately. If you want higher assurance, ask the author for implementation details (API endpoints, auth requirements) or a code-backed skill that uses an audited data provider.
Capability Analysis
Type: OpenClaw Skill
Name: china-stock-screener
Version: 1.0.0
The skill bundle provides structured instructions and reference criteria for a stock screening tool focused on Chinese and Hong Kong markets. It contains no executable code, shell commands, or data exfiltration logic, and the instructions in SKILL.md and references/screening-criteria.md are strictly aligned with financial analysis and reporting.
Capability Assessment
Purpose & Capability
Name, description, and SKILL.md all describe a multi‑factor stock screener for A‑share and HK markets. There are no requested binaries, environment variables, or config paths that would be unexpected for this purpose.
Instruction Scope
The SKILL.md gives detailed screening logic, templates, and output format but does not specify HOW to retrieve the market and funds data (no API endpoints, no authorized data sources or credentials). That makes runtime behavior implementation‑dependent (agent may need web access or scraping). The instructions do not tell the agent to read local files, environment variables, or other sensitive system state.
Install Mechanism
Instruction‑only skill with no install spec and no code files — nothing is written to disk or downloaded at install time.
Credentials
The skill requests no environment variables, credentials, or config paths. The lack of declared credentials is consistent with being an instruction template, though it means the agent must rely on available network/data access to function.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modifications to other skills. Autonomous invocation is allowed (platform default) but not combined with other red flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install china-stock-screener - After installation, invoke the skill by name or use
/china-stock-screener - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Stock Screener
Screen A-share and Hong Kong-listed stocks that meet specified criteria across three dimensions: technicals, capital flows, and fundamentals. Supports multi-factor stock selection, conditional filtering, and ranked output.
Metadata
Frequently Asked Questions
What is Stock Screener?
基于技术面、资金面、基本面三维度筛选A股和港股符合条件的股票。支持多因子选股、条件过滤、排序输出。 It is an AI Agent Skill for Claude Code / OpenClaw, with 568 downloads so far.
How do I install Stock Screener?
Run "/install china-stock-screener" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Stock Screener free?
Yes, Stock Screener is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Stock Screener support?
Stock Screener is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Stock Screener?
It is built and maintained by weqwhdiowa (@tingdall); the current version is v1.0.0.
More Skills