earnings-preview

Name: earnings-preview
Author: himself65

1.4kinstalls351forks

How to install earnings-preview?

himself65/finance-skills/earnings-preview

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

Installs into the current project.

Summary

Generate a pre-earnings briefing for any stock using Yahoo Finance data. Use this skill whenever the user wants to prepare for an upcoming earnings report, understand what analysts expect, review a company's beat/miss track record, or get a quick overview before an earnings call.

Files · 1

View on GitHub

SKILL.md

1	# Earnings Preview Skill
2
3	Generates a pre-earnings briefing using Yahoo Finance data via [yfinance](https://github.com/ranaroussi/yfinance). Pulls together upcoming earnings date, consensus estimates, historical accuracy, analyst sentiment, and key financial context — everything you need before an earnings call.
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 All Data
29
30	Extract the ticker symbol from the user's request. If they mention a company name without a ticker, look it up. Then fetch all relevant data in one script to minimize API calls.
31
32	```python
33	import yfinance as yf
34	import pandas as pd
35	from datetime import datetime
36
37	ticker = yf.Ticker("AAPL") # replace with actual ticker
38
39	# --- Core data ---
40	info = ticker.info
41	calendar = ticker.calendar
42
43	# --- Estimates ---
44	earnings_est = ticker.earnings_estimate
45	revenue_est = ticker.revenue_estimate
46
47	# --- Historical track record ---
48	earnings_hist = ticker.earnings_history
49
50	# --- Analyst sentiment ---
51	price_targets = ticker.analyst_price_targets
52	recommendations = ticker.recommendations
53
54	# --- Recent financials for context ---
55	quarterly_income = ticker.quarterly_income_stmt
56	quarterly_cashflow = ticker.quarterly_cashflow
57	```
58
59	### What to extract from each source
60
61	\| Data Source \| Key Fields \| Purpose \|
62	\|---\|---\|---\|
63	\| `calendar` \| Earnings Date, Ex-Dividend Date \| When earnings are and key dates \|
64	\| `earnings_estimate` \| avg, low, high, numberOfAnalysts, yearAgoEps, growth (for 0q, +1q, 0y, +1y) \| Consensus EPS expectations \|
65	\| `revenue_estimate` \| avg, low, high, numberOfAnalysts, yearAgoRevenue, growth \| Revenue expectations \|
66	\| `earnings_history` \| epsEstimate, epsActual, epsDifference, surprisePercent \| Beat/miss track record \|
67	\| `analyst_price_targets` \| current, low, high, mean, median \| Street price targets \|
68	\| `recommendations` \| Buy/Hold/Sell counts \| Sentiment distribution \|
69	\| `quarterly_income_stmt` \| TotalRevenue, NetIncome, BasicEPS \| Recent trajectory \|
70
71	---
72
73	## Step 3: Build the Earnings Preview
74
75	Assemble the data into a structured briefing. The goal is to give the user everything they need in one glance.
76
77	### Section 1: Earnings Date & Key Info
78
79	Report the upcoming earnings date from `calendar`. Include:
80	- Company name, ticker, sector, industry
81	- Upcoming earnings date (and whether it's before/after market)
82	- Current stock price and recent performance (1-week, 1-month)
83	- Market cap
84
85	### Section 2: Consensus Estimates
86
87	Present the current quarter estimates from `earnings_estimate` and `revenue_estimate`:
88
89	\| Metric \| Consensus \| Low \| High \| # Analysts \| Year Ago \| Growth \|
90	\|---\|---\|---\|---\|---\|---\|---\|
91	\| EPS \| $1.42 \| $1.35 \| $1.50 \| 28 \| $1.26 \| +12.7% \|
92	\| Revenue \| $94.3B \| $92.1B \| $96.8B \| 25 \| $89.5B \| +5.4% \|
93
94	If the estimate range is unusually wide (high/low spread > 20% of consensus), note that as a sign of high uncertainty.
95
96	### Section 3: Historical Beat/Miss Track Record
97
98	From `earnings_history`, show the last 4 quarters:
99
100	\| Quarter \| EPS Est \| EPS Actual \| Surprise \| Beat/Miss \|
101	\|---\|---\|---\|---\|---\|
102	\| Q3 2024 \| $1.35 \| $1.40 \| +3.7% \| Beat \|
103	\| Q2 2024 \| $1.30 \| $1.33 \| +2.3% \| Beat \|
104	\| Q1 2024 \| $1.52 \| $1.53 \| +0.7% \| Beat \|
105	\| Q4 2023 \| $2.10 \| $2.18 \| +3.8% \| Beat \|
106
107	Summarize: "AAPL has beaten EPS estimates in 4 of the last 4 quarters by an average of 2.6%."
108
109	### Section 4: Analyst Sentiment
110
111	From `recommendation

People who liked this also viewed

6 picks

Type

earnings-preview

1.4kinstalls351forks

View on GitHub

How to install earnings-preview?

himself65/finance-skills/earnings-preview

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Earnings Preview Skill
2
3	Generates a pre-earnings briefing using Yahoo Finance data via [yfinance](https://github.com/ranaroussi/yfinance). Pulls together upcoming earnings date, consensus estimates, historical accuracy, analyst sentiment, and key financial context — everything you need before an earnings call.
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 All Data
29
30	Extract the ticker symbol from the user's request. If they mention a company name without a ticker, look it up. Then fetch all relevant data in one script to minimize API calls.
31
32	```python
33	import yfinance as yf
34	import pandas as pd
35	from datetime import datetime
36
37	ticker = yf.Ticker("AAPL") # replace with actual ticker
38
39	# --- Core data ---
40	info = ticker.info
41	calendar = ticker.calendar
42
43	# --- Estimates ---
44	earnings_est = ticker.earnings_estimate
45	revenue_est = ticker.revenue_estimate
46
47	# --- Historical track record ---
48	earnings_hist = ticker.earnings_history
49
50	# --- Analyst sentiment ---
51	price_targets = ticker.analyst_price_targets
52	recommendations = ticker.recommendations
53
54	# --- Recent financials for context ---
55	quarterly_income = ticker.quarterly_income_stmt
56	quarterly_cashflow = ticker.quarterly_cashflow
57	```
58
59	### What to extract from each source
60
61	\| Data Source \| Key Fields \| Purpose \|
62	\|---\|---\|---\|
63	\| `calendar` \| Earnings Date, Ex-Dividend Date \| When earnings are and key dates \|
64	\| `earnings_estimate` \| avg, low, high, numberOfAnalysts, yearAgoEps, growth (for 0q, +1q, 0y, +1y) \| Consensus EPS expectations \|
65	\| `revenue_estimate` \| avg, low, high, numberOfAnalysts, yearAgoRevenue, growth \| Revenue expectations \|
66	\| `earnings_history` \| epsEstimate, epsActual, epsDifference, surprisePercent \| Beat/miss track record \|
67	\| `analyst_price_targets` \| current, low, high, mean, median \| Street price targets \|
68	\| `recommendations` \| Buy/Hold/Sell counts \| Sentiment distribution \|
69	\| `quarterly_income_stmt` \| TotalRevenue, NetIncome, BasicEPS \| Recent trajectory \|
70
71	---
72
73	## Step 3: Build the Earnings Preview
74
75	Assemble the data into a structured briefing. The goal is to give the user everything they need in one glance.
76
77	### Section 1: Earnings Date & Key Info
78
79	Report the upcoming earnings date from `calendar`. Include:
80	- Company name, ticker, sector, industry
81	- Upcoming earnings date (and whether it's before/after market)
82	- Current stock price and recent performance (1-week, 1-month)
83	- Market cap
84
85	### Section 2: Consensus Estimates
86
87	Present the current quarter estimates from `earnings_estimate` and `revenue_estimate`:
88
89	\| Metric \| Consensus \| Low \| High \| # Analysts \| Year Ago \| Growth \|
90	\|---\|---\|---\|---\|---\|---\|---\|
91	\| EPS \| $1.42 \| $1.35 \| $1.50 \| 28 \| $1.26 \| +12.7% \|
92	\| Revenue \| $94.3B \| $92.1B \| $96.8B \| 25 \| $89.5B \| +5.4% \|
93
94	If the estimate range is unusually wide (high/low spread > 20% of consensus), note that as a sign of high uncertainty.
95
96	### Section 3: Historical Beat/Miss Track Record
97
98	From `earnings_history`, show the last 4 quarters:
99
100	\| Quarter \| EPS Est \| EPS Actual \| Surprise \| Beat/Miss \|
101	\|---\|---\|---\|---\|---\|
102	\| Q3 2024 \| $1.35 \| $1.40 \| +3.7% \| Beat \|
103	\| Q2 2024 \| $1.30 \| $1.33 \| +2.3% \| Beat \|
104	\| Q1 2024 \| $1.52 \| $1.53 \| +0.7% \| Beat \|
105	\| Q4 2023 \| $2.10 \| $2.18 \| +3.8% \| Beat \|
106
107	Summarize: "AAPL has beaten EPS estimates in 4 of the last 4 quarters by an average of 2.6%."
108
109	### Section 4: Analyst Sentiment
110
111	From `recommendation

People who liked this also viewed

6 picks

Type