stock-correlation

Name: stock-correlation
Author: himself65

1.7kinstalls351forks

How to install stock-correlation?

himself65/finance-skills/stock-correlation

$npx -y skills add himself65/finance-skills --skill stock-correlation

Installs into the current project.

Summary

Analyze stock correlations to find related companies and trading pairs. Use when the user asks about correlated stocks, related companies, sector peers, trading pairs, or how two or more stocks move together. Triggers: "what correlates with NVDA", "find stocks related to AMD", "c

Files · 1

View on GitHub

SKILL.md

1	# Stock Correlation Analysis Skill
2
3	Finds and analyzes correlated stocks using historical price data from Yahoo Finance via [yfinance](https://github.com/ranaroussi/yfinance). Routes to specialized sub-skills based on user intent.
4
5	Important: This is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.
6
7	---
8
9	## Step 1: Ensure Dependencies Are Available
10
11	Current environment status:
12
13	```
14	!`python3 -c "import yfinance, pandas, numpy; print(f'yfinance={yfinance.__version__} pandas={pandas.__version__} numpy={numpy.__version__}')" 2>/dev/null \|\| echo "DEPS_MISSING"`
15	```
16
17	If `DEPS_MISSING`, install required packages before running any code:
18
19	```python
20	import subprocess, sys
21	subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance", "pandas", "numpy"])
22	```
23
24	If all dependencies are already installed, skip the install step and proceed directly.
25
26	---
27
28	## Step 2: Route to the Correct Sub-Skill
29
30	Classify the user's request and jump to the matching sub-skill section below.
31
32	\| User Request \| Route To \| Examples \|
33	\|---\|---\|---\|
34	\| Single ticker, wants to find related stocks \| Sub-Skill A: Co-movement Discovery \| "what correlates with NVDA", "find stocks related to AMD", "sympathy plays for TSLA" \|
35	\| Two or more specific tickers, wants relationship details \| Sub-Skill B: Return Correlation \| "correlation between AMD and NVDA", "how do LITE and COHR move together", "compare AAPL vs MSFT" \|
36	\| Group of tickers, wants structure/grouping \| Sub-Skill C: Sector Clustering \| "correlation matrix for FAANG", "cluster these semiconductor stocks", "sector peers for AMD" \|
37	\| Wants time-varying or conditional correlation \| Sub-Skill D: Realized Correlation \| "rolling correlation AMD NVDA", "when NVDA drops what else drops", "how has correlation changed" \|
38
39	If ambiguous, default to Sub-Skill A (Co-movement Discovery) for single tickers, or Sub-Skill B (Return Correlation) for two tickers.
40
41	### Defaults for all sub-skills
42
43	\| Parameter \| Default \|
44	\|---\|---\|
45	\| Lookback period \| `1y` (1 year) \|
46	\| Data interval \| `1d` (daily) \|
47	\| Correlation method \| Pearson \|
48	\| Minimum correlation threshold \| 0.60 \|
49	\| Number of results \| Top 10 \|
50	\| Return type \| Daily log returns \|
51	\| Rolling window \| 60 trading days \|
52
53	---
54
55	## Sub-Skill A: Co-movement Discovery
56
57	Goal: Given a single ticker, find stocks that move with it.
58
59	### A1: Build the peer universe
60
61	You need 15-30 candidates. Do not use hardcoded ticker lists — build the universe dynamically at runtime. See `references/sector_universes.md` for the full implementation. The approach:
62
63	1. Screen same-industry stocks using `yf.screen()` + `yf.EquityQuery` to find stocks in the same industry as the target
64	2. Broaden to sector if the industry screen returns fewer than 10 peers
65	3. Add thematic/adjacent industries — read the target's `longBusinessSummary` and screen 1-2 related industries (e.g., a semiconductor company → also screen semiconductor equipment)
66	4. Combine, deduplicate, remove target ticker
67
68	### A2: Compute correlations
69
70	```python
71	import yfinance as yf
72	import pandas as pd
73	import numpy as np
74
75	def discover_comovement(target_ticker, peer_tickers, period="1y"):
76	all_tickers = [target_ticker] + [t for t in peer_tickers if t != target_ticker]
77	data = yf.download(all_tickers, period=period, auto_adjust=True, progress=False)
78
79	# Extract close prices — yf.download returns MultiIndex (Price, Ticker) columns
80	closes = data["Close"].dropna(axis=1, thresh=max(60, len(data) // 2))
81
82	# Log returns
83	returns = np.log(closes / closes.shift(1)).dropna()
84	corr_series = returns.corr()[target_ticker].drop(target_ticker, errors="ignore")
85
86	# Rank by absolute correlation
87	ranked = corr_series.abs().sort_values(ascending=False)
88
89	result = pd.DataFrame({
90	"Ticker": ranked.index,
91	"Correlation": [round(corr_series[t], 4) for t in ranked.index],
92	})
93	return result, returns
94	```
95
96	### A3: Present results
97
98	Show a rank

People who liked this also viewed

6 picks

Type

stock-correlation

1.7kinstalls351forks

View on GitHub

How to install stock-correlation?

himself65/finance-skills/stock-correlation

$npx -y skills add himself65/finance-skills --skill stock-correlation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Stock Correlation Analysis Skill
2
3	Finds and analyzes correlated stocks using historical price data from Yahoo Finance via [yfinance](https://github.com/ranaroussi/yfinance). Routes to specialized sub-skills based on user intent.
4
5	Important: This is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.
6
7	---
8
9	## Step 1: Ensure Dependencies Are Available
10
11	Current environment status:
12
13	```
14	!`python3 -c "import yfinance, pandas, numpy; print(f'yfinance={yfinance.__version__} pandas={pandas.__version__} numpy={numpy.__version__}')" 2>/dev/null \|\| echo "DEPS_MISSING"`
15	```
16
17	If `DEPS_MISSING`, install required packages before running any code:
18
19	```python
20	import subprocess, sys
21	subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance", "pandas", "numpy"])
22	```
23
24	If all dependencies are already installed, skip the install step and proceed directly.
25
26	---
27
28	## Step 2: Route to the Correct Sub-Skill
29
30	Classify the user's request and jump to the matching sub-skill section below.
31
32	\| User Request \| Route To \| Examples \|
33	\|---\|---\|---\|
34	\| Single ticker, wants to find related stocks \| Sub-Skill A: Co-movement Discovery \| "what correlates with NVDA", "find stocks related to AMD", "sympathy plays for TSLA" \|
35	\| Two or more specific tickers, wants relationship details \| Sub-Skill B: Return Correlation \| "correlation between AMD and NVDA", "how do LITE and COHR move together", "compare AAPL vs MSFT" \|
36	\| Group of tickers, wants structure/grouping \| Sub-Skill C: Sector Clustering \| "correlation matrix for FAANG", "cluster these semiconductor stocks", "sector peers for AMD" \|
37	\| Wants time-varying or conditional correlation \| Sub-Skill D: Realized Correlation \| "rolling correlation AMD NVDA", "when NVDA drops what else drops", "how has correlation changed" \|
38
39	If ambiguous, default to Sub-Skill A (Co-movement Discovery) for single tickers, or Sub-Skill B (Return Correlation) for two tickers.
40
41	### Defaults for all sub-skills
42
43	\| Parameter \| Default \|
44	\|---\|---\|
45	\| Lookback period \| `1y` (1 year) \|
46	\| Data interval \| `1d` (daily) \|
47	\| Correlation method \| Pearson \|
48	\| Minimum correlation threshold \| 0.60 \|
49	\| Number of results \| Top 10 \|
50	\| Return type \| Daily log returns \|
51	\| Rolling window \| 60 trading days \|
52
53	---
54
55	## Sub-Skill A: Co-movement Discovery
56
57	Goal: Given a single ticker, find stocks that move with it.
58
59	### A1: Build the peer universe
60
61	You need 15-30 candidates. Do not use hardcoded ticker lists — build the universe dynamically at runtime. See `references/sector_universes.md` for the full implementation. The approach:
62
63	1. Screen same-industry stocks using `yf.screen()` + `yf.EquityQuery` to find stocks in the same industry as the target
64	2. Broaden to sector if the industry screen returns fewer than 10 peers
65	3. Add thematic/adjacent industries — read the target's `longBusinessSummary` and screen 1-2 related industries (e.g., a semiconductor company → also screen semiconductor equipment)
66	4. Combine, deduplicate, remove target ticker
67
68	### A2: Compute correlations
69
70	```python
71	import yfinance as yf
72	import pandas as pd
73	import numpy as np
74
75	def discover_comovement(target_ticker, peer_tickers, period="1y"):
76	all_tickers = [target_ticker] + [t for t in peer_tickers if t != target_ticker]
77	data = yf.download(all_tickers, period=period, auto_adjust=True, progress=False)
78
79	# Extract close prices — yf.download returns MultiIndex (Price, Ticker) columns
80	closes = data["Close"].dropna(axis=1, thresh=max(60, len(data) // 2))
81
82	# Log returns
83	returns = np.log(closes / closes.shift(1)).dropna()
84	corr_series = returns.corr()[target_ticker].drop(target_ticker, errors="ignore")
85
86	# Rank by absolute correlation
87	ranked = corr_series.abs().sort_values(ascending=False)
88
89	result = pd.DataFrame({
90	"Ticker": ranked.index,
91	"Correlation": [round(corr_series[t], 4) for t in ranked.index],
92	})
93	return result, returns
94	```
95
96	### A3: Present results
97
98	Show a rank

People who liked this also viewed

6 picks

Type