A股股票预测助手

基于实时价格和技术指标，智能预测A股股票明日走势并生成详细分析报告与可视化图表供参考。

Security Scan

The skill mostly matches its stated purpose (A‑share predictions) but includes several incoherent or risky elements — notably a hardcoded billing API key, undocumented payment behavior that will attempt to charge users, and unused/odd data‑fetch code — so proceed with caution.

Purpose & Capability

Name/description claim: real‑time A股 predictions via Kimi Finance. Code: predictor class, chart generator and a billing integration. Using Kimi Finance via subprocess is consistent with the stated data source, but the predictor actually uses a mocked _mock_predict in practice (real fetch_data is present but unused in predict). The presence of an integrated payment module is consistent with the SKILL.md pricing, but embedding a billing API key in code is disproportionate and risky.

Instruction Scope

SKILL.md describes only query/analysis UX and lists Kimi Finance and common Python libs. It does not document that the skill will: (1) attempt to verify/charge the user at runtime via an external billing endpoint and may exit if payment fails; (2) read SKILLPAY_USER_ID environment variable. The code also contains a fetch_data function that invokes subprocess to run the kimi_finance module and writes temp files, but predict() currently uses mock data instead — that mismatch is unexpected and grants the skill discretion to run subprocesses and create temp files without clear need.

Install Mechanism

No install spec (instruction-only install) and no downloads. All code is bundled with the skill. Runtime network calls (requests to skillpay.me) and subprocess invocation of a kimi_finance module are present but executed only at runtime; there is no high‑risk installer or external archive download in the manifest.

Credentials

Declared requirements: none. Actual code: uses os.environ.get('SKILLPAY_USER_ID') for billing and contains a hardcoded BILLING_API_KEY (sensitive secret) pointing to https://skillpay.me. That key in source is disproportionate and insecure (should not be embedded). The skill will contact an external billing service and can block execution if payment verification fails. No other credentials are required, but the undocumented env var and the embedded secret are notable red flags.

Persistence & Privilege

Skill is not always:true, does not request system‑wide changes, and does not modify other skills. It does perform network calls to an external billing API and may exit the process on unpaid use, but it does not ask for elevated system persistence.

What to consider before installing

This skill appears to do what it says (generate A‑share technical predictions and charts) but contains several concerning implementation choices. Before installing or running: (1) be aware the skill will attempt to verify/charge users via https://skillpay.me and will call charge endpoints automatically — it may abort if payment fails; (2) the code contains a hardcoded billing API key (embedded secret) — treat this as insecure and potentially leaking your service account if reused; (3) the SKILL.md does not document the SKILLPAY_USER_ID environment variable used at runtime; (4) the predictor currently uses mocked data by default while a fetch_data function exists that would invoke a local kimi_finance module via subprocess and create temp files — confirm how real data is fetched and ensure the required kimi_finance package is trusted; (5) consider contacting the author for clarification, remove the hardcoded key, and test in an isolated environment (no sensitive accounts) before granting access or using it with real funds.

智能分析A股股票走势，基于实时价格和技术指标（KDJ、RSI、MACD、MA、BOLL等）生成明日走势预测和可视化图表。

功能特点

• 📈 实时数据：获取股票实时价格、成交量、涨跌幅
• 📊 技术指标：自动计算 KDJ、RSI、MACD、MA、BOLL、CCI 等
• 🎯 走势预测：基于技术分析预测明日走势
• 📉 可视化：生成走势图和技术指标图表
• ⚠️ 风险提示：明确标注预测仅供参考

使用方法

分析单只股票

预测 000001 的走势
分析 600519 明天怎么走
300750 预测

分析多只股票

预测 000001,600519,300750 的走势
分析这三只股票：000001、600519、300750

查看技术指标

查看 000001 的技术指标
600519 的 KDJ 和 RSI 是多少

数据源

• 实时价格：Kimi Finance (iFind)
• 技术指标：KDJ、RSI、MACD、MA、BOLL、CCI、ROC、ATR 等
• 更新频率：实时（交易时间内）

预测逻辑

基于以下技术指标综合分析：

指标	用途	判断标准
KDJ	超买超卖	>80超买，<20超卖
RSI	强弱指标	>70强势，<30弱势
MACD	趋势判断	金叉看多，死叉看空
MA	均线支撑	价格在MA上方看多
BOLL	波动区间	触及上轨注意回调
CCI	趋势强度	>100强势，<-100弱势

输出示例

📊 股票走势预测报告 - 2026年4月1日

📈 泽宇智能 (301179)
   收盘价: ¥25.35 (+3.95%)
   技术指标: KDJ: 64.6 / RSI: 59.9 / MACD: 0.12
   明日预测: ¥25.72 (+1.5%)
   上涨概率: 65%
   分析: 今日放量上涨3.95%，突破短期均线。技术指标显示多头格局...

免责声明

⚠️ 风险提示：

• 本 Skill 提供的预测基于技术分析，仅供参考
• 不构成投资建议，不构成买卖依据
• 股市有风险，投资需谨慎
• 过往表现不代表未来收益

支持的股票代码

• 沪市：600XXX, 601XXX, 603XXX, 688XXX (科创板)
• 深市：000XXX (主板), 002XXX (中小板), 300XXX (创业板), 301XXX (创业板)
• 北交所：8XXXXX, 4XXXXX

代码格式：

• 直接输入 6位数字，自动识别市场
• 或输入完整代码如 000001.SZ、600519.SH

技术栈

• Python 3.8+
• Kimi Finance API (iFind)
• matplotlib (图表生成)
• pandas (数据处理)

定价

• ClawHub：0.01 USDT/次
• Coze：¥1/次 或 ¥9.9/月无限次

版本

• v1.0.0 - 初始版本
• 支持A股实时预测和技术分析

---

作者: @shenmeng
更新: 2026-03-31