← Back to Skills Marketplace
A Share Dashboard
by
superhhh1992-byte
· GitHub ↗
· v1.0.0
· MIT-0
97
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install a-share-dashboard
Description
A股智能看板 - 偏基本面选股 + 热点标注 + 持仓监控。Web Dashboard 形式的股票分析工具。
README (SKILL.md)
A股智能看板
Streamlit Web Dashboard，提供：
- 📊 每日选股池（基本面评分）
- 🔍 个股深度分析（K线图 + 评分）
- 🔥 热点板块追踪
- 💰 北向资金流向
- ⚙️ 持仓监控
使用方法
启动看板
cd ~/.openclaw/workspace/a-share-dashboard
streamlit run app.py
访问地址: http://localhost:8501
功能说明
| Tab | 功能 | 说明 |
|---|---|---|
| 每日选股 | 根据基本面评分筛选股票 | 支持价格、涨跌幅、换手率筛选 |
| 个股详情 | 输入代码查看深度分析 | K线图 + 均线 + 基本面评分 |
| 热点追踪 | 概念板块涨幅榜 | 自动标注热点板块 |
| 北向资金 | 外资流向数据 | 近5日净流入图表 |
| 持仓监控 | 输入持仓实时监控 | 盈亏计算 + 风险预警 |
持仓格式
在侧边栏输入持仓，每行一只：
代码,成本,数量
603618,45.00,500
002149,18.50,1000
数据源
- 行情数据: 东方财富 API
- 板块数据: AKShare
- 北向资金: AKShare
技术栈
- Streamlit 1.55+
- Plotly (K线图)
- AKShare (数据)
- Pandas (数据处理)
注意事项
- 数据每 5 分钟自动刷新
- 点击"刷新数据"可手动更新
- 基本面评分仅供参考，不构成投资建议
Usage Guidance
This skill appears to implement a legitimate stock dashboard, but it calls an undeclared, hard-coded script at /home/c1/.openclaw/workspace/skills/a-share-stock-dossier/scripts/a_share_snapshot.py when fetching data. Before installing or running: 1) Ask the publisher to document dependencies and provide the a_share_snapshot.py source (or include its logic) — do not run the dashboard until you can inspect that script. 2) If you plan to run it, do so in a sandboxed environment (isolated user account or container) because the external script will run with the agent's permissions and may access network or local files. 3) Remove or replace hard-coded absolute paths with configurable/declarative dependencies, or ensure the referenced skill is trusted. 4) The included venv file is unnecessary — verify the package wasn't copied from a personal environment. If the maintainer cannot justify or reveal the external script, treat this as risky and avoid running it.
Capability Analysis
Type: OpenClaw Skill
Name: a-share-dashboard
Version: 1.0.0
The skill uses 'subprocess.run' in 'app.py' to execute a hardcoded Python script located in a different skill's directory ('/home/c1/.openclaw/workspace/skills/a-share-stock-dossier/scripts/a_share_snapshot.py'). This cross-skill dependency and the use of shell execution for data retrieval are risky patterns. Additionally, the 'fetch_via_script' function is vulnerable to argument injection because user-provided stock codes are passed directly as command-line arguments without sanitization, which could be used to alter the behavior of the underlying script.
Capability Assessment
Purpose & Capability
Name/description (A股看板) match the UI and analysis code in app.py. However, the app relies on an external snapshot script at an absolute path (/home/c1/.openclaw/workspace/skills/a-share-stock-dossier/scripts/a_share_snapshot.py) that is not declared in SKILL.md, not included in the file manifest, and not documented as a dependency. Executing another skill's script is not obviously required by a dashboard and is an undeclared cross-skill dependency.
Instruction Scope
SKILL.md instructs only to run streamlit run app.py and lists data sources (东方财富 API, AKShare). It does not mention that app.py will run an external script via subprocess (fetch_via_script calling the SNAPSHOT_SCRIPT). That external script may perform network I/O or access local files—behavior not visible or declared in the SKILL.md. The instructions therefore omit a material runtime action (executing code at a hard-coded absolute path).
Install Mechanism
No install spec (instruction-only), which is low risk. However, the repository includes a venv/pyvenv.cfg file—an included virtualenv config with absolute home path—which is unnecessary for an instruction-only skill and suggests the package was packaged from a local environment. This is odd but not inherently malicious.
Credentials
The skill declares no required environment variables or credentials, which matches the SKILL.md. There are no obvious requests for unrelated credentials. That said, because the skill executes an external script, that script might require or access secrets (not declared here), so lack of declared env vars does not guarantee no secret access at runtime.
Persistence & Privilege
always is false and the skill does not claim to modify other skills or system-wide configs. The meaningful privilege concern is runtime: app.py executes another script from the workspace which can run arbitrary code with the agent user's privileges. That cross-script execution increases blast radius if the referenced script is untrusted.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install a-share-dashboard - After installation, invoke the skill by name or use
/a-share-dashboard - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of A股智能看板 (a-share-dashboard):
- Provides a web-based Streamlit dashboard for A股分析
- Features fundamental stock screening, hotspot sector tracking, and deep individual stock analysis with K-line charts
- Includes northbound capital flow tracking and real-time portfolio monitoring with risk alerts
- Supports customizable stock pools and interactive data refresh
- Utilizes 东方财富 and AKShare for market and sector data
Metadata
Frequently Asked Questions
What is A Share Dashboard?
A股智能看板 - 偏基本面选股 + 热点标注 + 持仓监控。Web Dashboard 形式的股票分析工具。 It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.
How do I install A Share Dashboard?
Run "/install a-share-dashboard" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is A Share Dashboard free?
Yes, A Share Dashboard is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does A Share Dashboard support?
A Share Dashboard is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created A Share Dashboard?
It is built and maintained by superhhh1992-byte (@superhhh1992-byte); the current version is v1.0.0.
More Skills