earnings-recap

Name: earnings-recap
Author: himself65

1.4kinstalls351forks

How to install earnings-recap?

himself65/finance-skills/earnings-recap

$npx -y skills add himself65/finance-skills --skill earnings-recap

Installs into the current project.

Summary

Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT

Files · 1

View on GitHub

SKILL.md

1	# Earnings Recap Skill
2
3	Generates a post-earnings analysis using Yahoo Finance data via [yfinance](https://github.com/ranaroussi/yfinance). Covers the actual vs estimated numbers, surprise magnitude, stock price reaction, and financial context — a complete picture of what happened.
4
5	Important: Data is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.
6
7	---
8
9	## Step 1: Ensure yfinance Is Available
10
11	Current environment status:
12
13	```
14	!`python3 -c "import yfinance; print('yfinance ' + yfinance.__version__ + ' installed')" 2>/dev/null \|\| echo "YFINANCE_NOT_INSTALLED"`
15	```
16
17	If `YFINANCE_NOT_INSTALLED`, install it:
18
19	```python
20	import subprocess, sys
21	subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])
22	```
23
24	If already installed, skip to the next step.
25
26	---
27
28	## Step 2: Identify the Ticker and Gather Data
29
30	Extract the ticker from the user's request. Fetch all relevant post-earnings data in one script.
31
32	```python
33	import yfinance as yf
34	import pandas as pd
35	from datetime import datetime, timedelta
36
37	ticker = yf.Ticker("AAPL") # replace with actual ticker
38
39	# --- Earnings result ---
40	earnings_hist = ticker.earnings_history
41
42	# --- Financial statements ---
43	quarterly_income = ticker.quarterly_income_stmt
44	quarterly_cashflow = ticker.quarterly_cashflow
45	quarterly_balance = ticker.quarterly_balance_sheet
46
47	# --- Price reaction ---
48	# Get ~30 days of history to capture the reaction window
49	hist = ticker.history(period="1mo")
50
51	# --- Context ---
52	info = ticker.info
53	news = ticker.news
54	recommendations = ticker.recommendations
55	```
56
57	### What to extract
58
59	\| Data Source \| Key Fields \| Purpose \|
60	\|---\|---\|---\|
61	\| `earnings_history` \| epsEstimate, epsActual, epsDifference, surprisePercent \| Beat/miss result \|
62	\| `quarterly_income_stmt` \| TotalRevenue, GrossProfit, OperatingIncome, NetIncome, BasicEPS \| Actual financials \|
63	\| `history()` \| Close prices around earnings date \| Stock price reaction \|
64	\| `info` \| currentPrice, marketCap, forwardPE \| Current context \|
65	\| `news` \| Recent headlines \| Earnings-related news \|
66
67	---
68
69	## Step 3: Determine the Most Recent Earnings
70
71	The most recent earnings result is the first row (most recent date) in `earnings_history`. Use its date to:
72
73	1. Identify the earnings date for the price reaction analysis
74	2. Match to the corresponding quarter in the financial statements
75	3. Calculate stock price reaction — compare the close before earnings to the next trading day's close (or open, depending on whether earnings were before/after market)
76
77	### Price reaction calculation
78
79	```python
80	import numpy as np
81
82	# Find the earnings date from earnings_history index
83	earnings_date = earnings_hist.index[0] # most recent
84
85	# Get daily prices around the earnings date
86	hist_extended = ticker.history(start=earnings_date - timedelta(days=5),
87	end=earnings_date + timedelta(days=5))
88
89	# The reaction is typically measured as:
90	# - Close on the last trading day before earnings -> Close on the first trading day after
91	# Be careful with before/after market reports
92	if len(hist_extended) >= 2:
93	pre_price = hist_extended['Close'].iloc[0]
94	post_price = hist_extended['Close'].iloc[-1]
95	reaction_pct = ((post_price - pre_price) / pre_price) * 100
96	```
97
98	Note: The exact reaction window depends on when the company reported (before market open vs after close). The price data will reflect this — look for the biggest gap between consecutive closes near the earnings date.
99
100	---
101
102	## Step 4: Build the Earnings Recap
103
104	### Section 1: Headline Result
105
106	Lead with the key numbers:
107	- EPS: Actual vs. Estimate, beat/miss by how much, surprise %
108	- Revenue: Actual vs. prior year (from quarterly_income_stmt TotalRevenue)
109	- Stock reaction: % move on earnings day
110
111	Example: "AAPL beat Q3 EPS estimates by 3.7% ($1.40 actual vs $1.35 expected). Revenue grew 5.4% YoY to $94.3B. The stock rose +2.1% on the report."
112
113	### Section 2: Earnings vs. Estimates Detail
114
115	\| Metric \| Estimate \| Actual \| Surprise \|
116	\|---\|---\|---\|---\|
117	\| EPS \| $1.35 \| $1.40 \| +$0.05 (+3.7%) \|
118
119	If the user asked about a specific quar

People who liked this also viewed

6 picks

Type

earnings-recap

1.4kinstalls351forks

View on GitHub

How to install earnings-recap?

himself65/finance-skills/earnings-recap

$npx -y skills add himself65/finance-skills --skill earnings-recap

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Earnings Recap Skill
2
3	Generates a post-earnings analysis using Yahoo Finance data via [yfinance](https://github.com/ranaroussi/yfinance). Covers the actual vs estimated numbers, surprise magnitude, stock price reaction, and financial context — a complete picture of what happened.
4
5	Important: Data is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.
6
7	---
8
9	## Step 1: Ensure yfinance Is Available
10
11	Current environment status:
12
13	```
14	!`python3 -c "import yfinance; print('yfinance ' + yfinance.__version__ + ' installed')" 2>/dev/null \|\| echo "YFINANCE_NOT_INSTALLED"`
15	```
16
17	If `YFINANCE_NOT_INSTALLED`, install it:
18
19	```python
20	import subprocess, sys
21	subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])
22	```
23
24	If already installed, skip to the next step.
25
26	---
27
28	## Step 2: Identify the Ticker and Gather Data
29
30	Extract the ticker from the user's request. Fetch all relevant post-earnings data in one script.
31
32	```python
33	import yfinance as yf
34	import pandas as pd
35	from datetime import datetime, timedelta
36
37	ticker = yf.Ticker("AAPL") # replace with actual ticker
38
39	# --- Earnings result ---
40	earnings_hist = ticker.earnings_history
41
42	# --- Financial statements ---
43	quarterly_income = ticker.quarterly_income_stmt
44	quarterly_cashflow = ticker.quarterly_cashflow
45	quarterly_balance = ticker.quarterly_balance_sheet
46
47	# --- Price reaction ---
48	# Get ~30 days of history to capture the reaction window
49	hist = ticker.history(period="1mo")
50
51	# --- Context ---
52	info = ticker.info
53	news = ticker.news
54	recommendations = ticker.recommendations
55	```
56
57	### What to extract
58
59	\| Data Source \| Key Fields \| Purpose \|
60	\|---\|---\|---\|
61	\| `earnings_history` \| epsEstimate, epsActual, epsDifference, surprisePercent \| Beat/miss result \|
62	\| `quarterly_income_stmt` \| TotalRevenue, GrossProfit, OperatingIncome, NetIncome, BasicEPS \| Actual financials \|
63	\| `history()` \| Close prices around earnings date \| Stock price reaction \|
64	\| `info` \| currentPrice, marketCap, forwardPE \| Current context \|
65	\| `news` \| Recent headlines \| Earnings-related news \|
66
67	---
68
69	## Step 3: Determine the Most Recent Earnings
70
71	The most recent earnings result is the first row (most recent date) in `earnings_history`. Use its date to:
72
73	1. Identify the earnings date for the price reaction analysis
74	2. Match to the corresponding quarter in the financial statements
75	3. Calculate stock price reaction — compare the close before earnings to the next trading day's close (or open, depending on whether earnings were before/after market)
76
77	### Price reaction calculation
78
79	```python
80	import numpy as np
81
82	# Find the earnings date from earnings_history index
83	earnings_date = earnings_hist.index[0] # most recent
84
85	# Get daily prices around the earnings date
86	hist_extended = ticker.history(start=earnings_date - timedelta(days=5),
87	end=earnings_date + timedelta(days=5))
88
89	# The reaction is typically measured as:
90	# - Close on the last trading day before earnings -> Close on the first trading day after
91	# Be careful with before/after market reports
92	if len(hist_extended) >= 2:
93	pre_price = hist_extended['Close'].iloc[0]
94	post_price = hist_extended['Close'].iloc[-1]
95	reaction_pct = ((post_price - pre_price) / pre_price) * 100
96	```
97
98	Note: The exact reaction window depends on when the company reported (before market open vs after close). The price data will reflect this — look for the biggest gap between consecutive closes near the earnings date.
99
100	---
101
102	## Step 4: Build the Earnings Recap
103
104	### Section 1: Headline Result
105
106	Lead with the key numbers:
107	- EPS: Actual vs. Estimate, beat/miss by how much, surprise %
108	- Revenue: Actual vs. prior year (from quarterly_income_stmt TotalRevenue)
109	- Stock reaction: % move on earnings day
110
111	Example: "AAPL beat Q3 EPS estimates by 3.7% ($1.40 actual vs $1.35 expected). Revenue grew 5.4% YoY to $94.3B. The stock rose +2.1% on the report."
112
113	### Section 2: Earnings vs. Estimates Detail
114
115	\| Metric \| Estimate \| Actual \| Surprise \|
116	\|---\|---\|---\|---\|
117	\| EPS \| $1.35 \| $1.40 \| +$0.05 (+3.7%) \|
118
119	If the user asked about a specific quar

People who liked this also viewed

6 picks

Type