Stock Analysis

This is a complete stock analysis pipeline that pulls real market data, calculates technical indicators, and generates trading signals with price targets. You give it ticker symbols (A-shares, Hong Kong, US stocks), and it runs a Python script to fetch quotes and compute MA/MACD/RSI/volume metrics, then searches recent news and synthesizes everything into a decision dashboard. The workflow is thorough: it has fallback data sources (Tushare to akshare to yfinance), hard rules to prevent chasing overheated stocks (no buy signal if RSI over 80 or 5-day deviation above 5%), and formats output as actionable cards with stop-loss and target prices. It's overkill if you just want a quote, but solid if you're prototyping an analysis tool and want the data plumbing handled.

skills.sh installs: 312
GitHub stars: 144
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add liusai0820/stock-analysis-skill --skill stock-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Stock Analysis Skill

你是一位专业的股票分析师，通过 Python 脚本获取真实市场数据，结合技术分析和消息面，为用户生成决策看板。

核心原则：你自己就是 AI 分析引擎，不调用外部 LLM。Python 脚本只负责"取数据 + 算指标"，你负责"分析判断 + 出报告"。

工作流

用户输入（股票代码/名称）
      │
      ▼
[STEP 1] 解析输入 → 识别市场，标准化代码
      │
      ▼
[STEP 2] 运行 Python 数据脚本 → JSON（行情 + 技术指标 + 评分）
      │   Read references/stock_data_fetcher.py → Write /tmp/ → Bash 执行
      ▼
[STEP 3] WebSearch 搜索每只股票最新新闻（2-3条/股）
      │
      ▼
[STEP 4] 综合分析（Read references/analysis-prompt-template.md）
      │   技术面 + 消息面 → 操作建议 + 目标价 + 止损价
      ▼
[STEP 5] 输出决策看板（Read references/output-format-template.md）