← 返回 Skills 市场

A Stock Trading Assistant

Name: A Stock Trading Assistant
Author: marjoriebroad

作者 MarjorieBroad · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install marjorie-a-stock-trading-assistant

功能描述

提供中国沪深A股实时行情、大盘情绪、个股技术与基本面分析、热点板块、交易策略及价格预警服务。

使用说明 (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

安全使用建议

This skill appears to do what it claims: fetch A‑share market data and produce analyses from public Chinese finance APIs, and it does not ask for credentials. Before installing, consider: 1) The SKILL.md mentions saving watchlists to references/watchlist.md and proactive alert checking, but that file is not present and the script does not obviously persist alerts — if you need persistent alerts, ask the author how alerts are stored and how background checking is performed. 2) The skill makes outbound network requests to public finance sites (sina, eastmoney, 10jqka, xueqiu); ensure you are comfortable with the agent making those calls (rate limits, legal/terms of service for scraping). 3) The SKILL.md claims Xueqiu cookie handling; verify the code indeed obtains/uses cookies correctly if you rely on Xueqiu data. 4) If you plan to run this in an environment with sensitive data, sandbox the skill first (it will make external HTTP requests). 5) If you want scheduled monitoring or push notifications, require the author to implement explicit persistence and document where data are stored and how long they are kept.

功能分析

Type: OpenClaw Skill Name: marjorie-a-stock-trading-assistant Version: 1.0.0 The skill bundle is a legitimate A-share stock trading assistant. The core logic in `scripts/fetch_stock.py` uses Python's standard library to fetch real-time market data from public financial APIs (Sina Finance and EastMoney) without any suspicious external dependencies or obfuscation. The instructions in `SKILL.md` and the supporting documentation in the `references/` directory are well-structured, align with the stated purpose of financial analysis, and do not contain any prompt-injection attempts or requests for sensitive system access.

能力评估

✓ Purpose & Capability

Name/description (A‑share trading assistant) match the provided code and data-source references. The included Python script and documented APIs (新浪/东方财富/同花顺/雪球) are appropriate and expected for real‑time A‑share data fetching and analysis. No unrelated credentials, binaries, or system access are requested.

ℹ Instruction Scope

SKILL.md instructs the agent to run scripts/fetch_stock.py and to fetch directly from listed data sources — this aligns with purpose. Minor scope mismatches: SKILL.md says it will 'record target price/preconditions to references/watchlist.md' and that the script handles Xueqiu cookie/session acquisition and a 'web_fetch' fallback; the repository does not include references/watchlist.md in the manifest, and the visible portion of fetch_stock.py does not clearly implement persistent watchlist management. These are implementation omissions rather than malicious actions, but they affect behavior (persistence/alerting) claimed in the documentation.

✓ Install Mechanism

No install spec is provided (instruction-only + a single Python script). Nothing is downloaded or written to disk by an installer. This low‑risk approach is proportional for the skill's purpose.

✓ Credentials

The skill requests no environment variables, credentials, or config paths. The network calls are limited to public finance data APIs (sina, eastmoney, 10jqka, xueqiu) appropriate for fetching market data. No sensitive secrets are requested.

ℹ Persistence & Privilege

always:false (no forced global inclusion) and autonomous invocation is allowed (platform default). SKILL.md implies persistent watchlist recording and later proactive checking of alerts, but the codebase does not show a background scheduler or explicit persistence file in the manifest; if the skill were extended to run background jobs or write persistent alerts, additional privileges/clarity would be needed. As provided, it does not request elevated persistence.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install marjorie-a-stock-trading-assistant
安装完成后，直接呼叫该 Skill 的名称或使用 /marjorie-a-stock-trading-assistant 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release

元数据

Slug marjorie-a-stock-trading-assistant

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