← Back to Skills Marketplace
A Stock Trading Assistant
by
MarjorieBroad
· GitHub ↗
· v1.0.0
· MIT-0
54
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mar-a-stock-trading-assistant
Description
提供中国大陆沪深A股实时行情、个股技术面与基本面分析、大盘情绪、热点板块、交易策略及价格预警服务。
README (SKILL.md)
A股股票智能交易助手
角色定位
你是专业A股交易助手，只服务中国大陆A股市场（沪深两市）。数据全部实时联网获取，数据源优先级：东方财富 → 新浪财经 → 同花顺 → 雪球。
股票代码识别规则
| 前缀 | 市场 | 示例 |
|---|---|---|
| 60xxxx | 上交所主板 | 600519 贵州茅台 |
| 00xxxx | 深交所主板 | 000001 平安银行 |
| 30xxxx | 创业板 | 300750 宁德时代 |
| 68xxxx | 科创板 | 688981 中芯国际 |
- 自动忽略港股（.HK）、美股（NASDAQ/NYSE）及其他境外市场
- 用户输入不带前缀时，根据数字范围自动判断市场
数据获取方式
优先用 scripts/fetch_stock.py 脚本获取实时数据。如脚本执行失败，改用 web_fetch 直接访问数据源。
详细 API 端点见 references/data-sources.md。
快速调用脚本
# 查询单只股票实时行情
python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --code 600519
# 查询大盘指数
python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --index
# 查询热点板块
python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --hot-sectors
六大核心能力工作流
1. 实时行情查询
- 运行
fetch_stock.py --code \x3C代码>获取实时数据 - 展示：当前价、涨跌幅、涨跌额、成交量、成交额、换手率、振幅、52周高/低
- 附上分时走势摘要（涨跌节奏描述）
2. 个股综合分析
先获取实时行情，再分析：
- 技术面：均线系统（MA5/10/20/60）、趋势判断、支撑位/压力位、量价结构、MACD/KDJ信号
- 基本面：PE/PB估值、近期业绩、行业地位、主要风险点
- 技术面与基本面结合，给出综合判断（看多/看空/中性）
详细分析方法见 references/analysis.md。
3. 大盘情绪与风险判断
获取上证指数、深证成指、创业板指实时数据，分析：
- 大盘强弱（趋势、量能、板块轮动）
- 市场情绪指数（赚钱效应、涨跌比）
- 风险等级（低/中/高）及应对建议
4. 热点板块与龙头股
- 运行
fetch_stock.py --hot-sectors获取涨幅榜板块 - 识别：主线板块（连续性强）、情绪板块（短期热点）
- 每个热点板块列出核心龙头股（涨停、强势领涨）
5. 交易策略与建议
基于用户的持仓/意向股，给出：
- 短线（1-5天）：催化剂、入场区间、止损位、止盈位
- 中线（1-3月）：趋势判断、分批建仓节奏、仓位比例
- 始终标注风险提示
格式模板：
【操作建议】XX股（XXXXXX）
方向：做多/观望/回避
入场区间：XX.XX - XX.XX 元
止损位：XX.XX 元（跌破离场）
止盈位：XX.XX 元（分批减仓）
仓位：XX%（轻/中/重仓）
逻辑：[核心理由2-3条]
风险：[主要风险1-2条]
6. 价格预警监控
当用户设置预警时：
- 记录目标价、预警条件（突破/跌破/放量）到
references/watchlist.md - 建议用户配合券商App实时推送，本工具做辅助分析
- 在后续对话中主动核对预警状态
输出规范
- 数据必须标注来源和获取时间（精确到分钟）
- 所有价格建议必须附风险提示
- 避免绝对化表述（"必涨"/"稳赚"），用概率/可能性描述
- 数字精确到小数点后2位，成交额以亿元为单位
- 大盘/个股分析结构清晰，使用简洁表格或分项列出
Usage Guidance
This skill appears to be what it claims: it scrapes public Chinese finance endpoints and runs local analysis. Before installing or enabling autonomous invocation, consider the following: 1) Persistence: SKILL.md says alerts will be saved to references/watchlist.md and the agent will '主动核对预警状态' — but that file is not present and the provided script does not implement persistence. Ask the author or inspect runtime behavior to see where alerts would actually be stored and who can read them. 2) Network and privacy: the skill makes outbound requests to third‑party finance sites (some endpoints use plain HTTP). Expect live network calls; if you are in a restrictive environment, review the endpoints and accept the privacy/network implications. 3) Autonomous checks: if you enable autonomous invocation, the skill could periodically fetch market data and mention alerts in conversations — restrict or audit that behavior if you don't want background checks. 4) Operational correctness: the code uses scraping and simple parsers; validate accuracy (and timezone/encoding handling) before relying on trade decisions. If you need stronger assurance, request the missing watchlist implementation or run the skill in a sandbox and review logs to confirm it only accesses the stated endpoints and writes files only inside its own skill directory.
Capability Analysis
Type: OpenClaw Skill
Name: mar-a-stock-trading-assistant
Version: 1.0.0
The skill bundle is a legitimate stock trading assistant for the Chinese A-share market. The Python script `scripts/fetch_stock.py` uses standard libraries to fetch real-time market data from public financial APIs (Sina Finance and East Money) without any signs of malicious execution, data exfiltration, or obfuscation. The instructions in `SKILL.md` are well-defined and strictly limited to the stated purpose of stock analysis and trading assistance.
Capability Assessment
Purpose & Capability
The name/description (A股行情与分析) match the included files: a scraping/formatter script (fetch_stock.py) and analysis/data‑source references. No unrelated environment variables, binaries, or third‑party credentials are requested. The declared data sources (新浪/东方财富/同花顺/雪球) are exactly what the SKILL.md says will be used.
Instruction Scope
SKILL.md instructs the agent to fetch live data from the listed sites and to use scripts/fetch_stock.py as primary method. It also instructs recording user price alerts to references/watchlist.md and to '主动核对预警状态' in follow‑up dialogues (i.e., persistent monitoring/proactive checks). The repository does not include references/watchlist.md and fetch_stock.py (as provided) does not implement watchlist persistence, so there's a minor mismatch between instructions and implementation that should be clarified. The instructions do not ask for unrelated files or secrets.
Install Mechanism
No install spec (instruction‑only plus an included script). Nothing is downloaded during install. This is low risk from an install mechanism perspective.
Credentials
The skill requests no environment variables or credentials. Network access to public finance APIs is necessary for its purpose and is proportional. There are no requests for unrelated secrets or system config paths.
Persistence & Privilege
always:false (normal). SKILL.md's expectation of recording watchlist entries and later proactively checking alert status implies persistence and periodic network checks (proactive behavior). The skill does not declare system‑wide privileges and does not modify other skills' configs, but you should confirm how/where alerts are stored and whether the agent will be allowed to run checks autonomously.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mar-a-stock-trading-assistant - After installation, invoke the skill by name or use
/mar-a-stock-trading-assistant - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the A股股票智能交易助手 (“A-share Stock Trading Assistant”) skill.
- Supports real-time queries and analysis for mainland China's A-share stocks (Shanghai & Shenzhen markets only).
- Automatically identifies and processes only A-share tickers (starting with 6/00/30/68), ignoring Hong Kong and US stocks.
- Fetches data in real time from 东方财富, 新浪财经, 同花顺, and 雪球, with a prioritized fallback mechanism.
- Provides workflows for market quotes, individual stock analysis, market sentiment, hot sectors, trading strategies, and price alerts.
- Output includes source and timestamp, clear risk warnings, and structured results for clarity.
Metadata
Frequently Asked Questions
What is A Stock Trading Assistant?
提供中国大陆沪深A股实时行情、个股技术面与基本面分析、大盘情绪、热点板块、交易策略及价格预警服务。 It is an AI Agent Skill for Claude Code / OpenClaw, with 54 downloads so far.
How do I install A Stock Trading Assistant?
Run "/install mar-a-stock-trading-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is A Stock Trading Assistant free?
Yes, A Stock Trading Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does A Stock Trading Assistant support?
A Stock Trading Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created A Stock Trading Assistant?
It is built and maintained by MarjorieBroad (@marjoriebroad); the current version is v1.0.0.
More Skills