claude-code/claude-finance/skills/chart-drawing/SKILL.md

name	description
chart-drawing	技術分析圖表繪製知識庫。用 Python matplotlib 繪製各種技術型態圖，每種型態分開畫，輸出 PNG 圖片。

技術分析圖表繪製

環境需求

pip install yfinance matplotlib mplfinance pandas numpy

數據取得

import yfinance as yf

# 美股
df = yf.download("NVDA", period="1y", interval="1d")

# 台股（代號加 .TW）
df = yf.download("2330.TW", period="1y", interval="1d")

核心原則

1. 每種型態分開畫 — 不要把所有東西混在一張圖上
2. 圖片要清晰 — 至少 1200x800 像素，字體夠大
3. 標註關鍵價位 — 支撐、壓力、進場點用不同顏色標示
4. 存成 PNG — 存到 docs/fin/charts/ 目錄下

圖表類型與範本

1. K 線圖 + 均線（基礎圖）

import mplfinance as mpf
import yfinance as yf

df = yf.download("NVDA", period="6mo", interval="1d")

mpf.plot(df, type='candle', style='charles',
         mav=(20, 50, 200),
         volume=True,
         title='NVDA K線圖 + 均線',
         figsize=(14, 8),
         savefig='docs/fin/charts/NVDA-kline.png')

2. 支撐壓力圖

import matplotlib.pyplot as plt
import yfinance as yf

df = yf.download("NVDA", period="6mo", interval="1d")
close = df['Close'].values.flatten()
dates = df.index

fig, ax = plt.subplots(figsize=(14, 8))
ax.plot(dates, close, 'b-', linewidth=1.5, label='收盤價')

# 標註支撐壓力（需手動或演算法計算）
support = 120   # 範例值
resistance = 150
ax.axhline(y=support, color='green', linestyle='--', label=f'支撐 ${support}')
ax.axhline(y=resistance, color='red', linestyle='--', label=f'壓力 ${resistance}')

ax.set_title('NVDA 支撐壓力圖', fontsize=16)
ax.legend(fontsize=12)
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('docs/fin/charts/NVDA-support-resistance.png', dpi=150)
plt.show()

3. RSI 圖

import matplotlib.pyplot as plt
import yfinance as yf
import pandas as pd

df = yf.download("NVDA", period="6mo", interval="1d")
close = df['Close'].squeeze()
delta = close.diff()
gain = delta.where(delta > 0, 0).rolling(14).mean()
loss = (-delta.where(delta < 0, 0)).rolling(14).mean()
rs = gain / loss
rsi = 100 - (100 / (1 + rs))

fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(14, 10), height_ratios=[3, 1])
ax1.plot(df.index, close, 'b-', linewidth=1.5)
ax1.set_title('NVDA 股價', fontsize=14)
ax1.grid(True, alpha=0.3)

ax2.plot(df.index, rsi, 'purple', linewidth=1.5)
ax2.axhline(y=70, color='red', linestyle='--', alpha=0.7, label='超買 70')
ax2.axhline(y=30, color='green', linestyle='--', alpha=0.7, label='超賣 30')
ax2.fill_between(df.index, 70, 100, alpha=0.1, color='red')
ax2.fill_between(df.index, 0, 30, alpha=0.1, color='green')
ax2.set_title('RSI(14)', fontsize=14)
ax2.set_ylim(0, 100)
ax2.legend()
ax2.grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('docs/fin/charts/NVDA-rsi.png', dpi=150)
plt.show()

4. MACD 圖

import matplotlib.pyplot as plt
import yfinance as yf

df = yf.download("NVDA", period="6mo", interval="1d")
close = df['Close'].squeeze()
ema12 = close.ewm(span=12).mean()
ema26 = close.ewm(span=26).mean()
macd_line = ema12 - ema26
signal = macd_line.ewm(span=9).mean()
histogram = macd_line - signal

fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(14, 10), height_ratios=[3, 1])
ax1.plot(df.index, close, 'b-', linewidth=1.5)
ax1.set_title('NVDA 股價', fontsize=14)
ax1.grid(True, alpha=0.3)

ax2.plot(df.index, macd_line, 'b-', label='MACD', linewidth=1.5)
ax2.plot(df.index, signal, 'r-', label='Signal', linewidth=1.5)
colors = ['green' if v >= 0 else 'red' for v in histogram]
ax2.bar(df.index, histogram, color=colors, alpha=0.5, label='Histogram')
ax2.set_title('MACD', fontsize=14)
ax2.legend()
ax2.grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('docs/fin/charts/NVDA-macd.png', dpi=150)
plt.show()

5. 布林通道圖

import matplotlib.pyplot as plt
import yfinance as yf

df = yf.download("NVDA", period="6mo", interval="1d")
close = df['Close'].squeeze()
sma20 = close.rolling(20).mean()
std20 = close.rolling(20).std()
upper = sma20 + 2 * std20
lower = sma20 - 2 * std20

fig, ax = plt.subplots(figsize=(14, 8))
ax.plot(df.index, close, 'b-', linewidth=1.5, label='收盤價')
ax.plot(df.index, sma20, 'orange', linewidth=1, label='SMA(20)')
ax.plot(df.index, upper, 'red', linewidth=0.8, linestyle='--', label='上軌')
ax.plot(df.index, lower, 'green', linewidth=0.8, linestyle='--', label='下軌')
ax.fill_between(df.index, upper, lower, alpha=0.1, color='gray')

ax.set_title('NVDA 布林通道', fontsize=16)
ax.legend(fontsize=12)
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('docs/fin/charts/NVDA-bollinger.png', dpi=150)
plt.show()

型態辨識圖（手動標註）

當 technical-analyst 識別出型態時，用以下模板繪製：

頭肩頂/底、雙頂/底、三角收斂等

# 通用型態標註模板
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import yfinance as yf