Earnings Recap

Earnings Recap Skill

Generates a post-earnings analysis using Yahoo Finance data via yfinance. Covers the actual vs estimated numbers, surprise magnitude, stock price reaction, and financial context — a complete picture of what happened.

Important: Data is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.

---

Step 1: Ensure yfinance Is Available

Current environment status:

!`python3 -c "import yfinance; print('yfinance ' + yfinance.__version__ + ' installed')" 2>/dev/null || echo "YFINANCE_NOT_INSTALLED"`

If YFINANCE_NOT_INSTALLED, install it:

import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])

If already installed, skip to the next step.

---

Step 2: Identify the Ticker and Gather Data

Extract the ticker from the user's request. Fetch all relevant post-earnings data in one script.

import yfinance as yf
import pandas as pd
from datetime import datetime, timedelta

ticker = yf.Ticker("AAPL")  # replace with actual ticker

# --- Earnings result ---
earnings_hist = ticker.earnings_history

# --- Financial statements ---
quarterly_income = ticker.quarterly_income_stmt
quarterly_cashflow = ticker.quarterly_cashflow
quarterly_balance = ticker.quarterly_balance_sheet

# --- Price reaction ---
# Get ~30 days of history to capture the reaction window
hist = ticker.history(period="1mo")

# --- Context ---
info = ticker.info
news = ticker.news
recommendations = ticker.recommendations

What to extract

---

Step 3: Determine the Most Recent Earnings

The most recent earnings result is the first row (most recent date) in earnings_history. Use its date to:

1. Identify the earnings date for the price reaction analysis 2. Match to the corresponding quarter in the financial statements 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)

Price reaction calculation

import numpy as np

# Find the earnings date from earnings_history index
earnings_date = earnings_hist.index[0]  # most recent

# Get daily prices around the earnings date
hist_extended = ticker.history(start=earnings_date - timedelta(days=5),
                                end=earnings_date + timedelta(days=5))

# The reaction is typically measured as:
# - Close on the last trading day before earnings -> Close on the first trading day after
# Be careful with before/after market reports
if len(hist_extended) >= 2:
    pre_price = hist_extended['Close'].iloc[0]
    post_price = hist_extended['Close'].iloc[-1]
    reaction_pct = ((post_price - pre_price) / pre_price) * 100

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.

---

Step 4: Build the Earnings Recap

Section 1: Headline Result

Lead with the key numbers:

• EPS: Actual vs. Estimate, beat/miss by how much, surprise %
• Revenue: Actual vs. prior year (from quarterly_income_stmt TotalRevenue)
• Stock reaction: % move on earnings day

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."

Section 2: Earnings vs. Estimates Detail

If the user asked about a specific quarter (not the most recent), look further back in earnings_history.

Section 3: Quarterly Financial Trends

Show the last 4 quarters of key metrics from quarterly_income_stmt:

Calculate margins from the raw financials:

• Gross Margin = GrossProfit / TotalRevenue
• Operating Margin = OperatingIncome / TotalRevenue

Section 4: Stock Price Reaction

• The % move on the earnings day/next session
• How it compares to the stock's average earnings-day move (calculate the average absolute move from the last 4 earnings dates in earnings_history)
• Where the stock is now relative to the earnings-day move (has it held, given back gains, extended further?)

Section 5: Context & What Changed

Based on the data, note:

• Whether margins expanded or compressed vs prior quarter
• Any notable changes in revenue growth trajectory
• How the beat/miss compares to the stock's historical pattern (from the full earnings_history)
• Current analyst sentiment from recommendations if available

---

Step 5: Respond to the User

Present the recap as a clean, structured summary:

1. Lead with the headline: "AAPL reported Q3 2024 earnings on [date]: Beat EPS by 3.7%, revenue +5.4% YoY." 2. Show the tables for detail 3. Highlight what matters: Was this a meaningful beat or a low-bar situation? Is the trend improving or deteriorating? 4. Keep it factual — present the data, avoid making investment recommendations

Caveats to include

• Yahoo Finance data may not include all details from the earnings call (guidance, segment breakdowns)
• Revenue estimates are harder to compare precisely — yfinance provides YoY comparison from financial statements
• Price reaction may be influenced by broader market moves on the same day
• This is not financial advice

---

Reference Files

• references/api_reference.md — Detailed yfinance API reference for earnings history and financial statement methods

Read the reference file when you need exact method signatures or to handle edge cases in the financial data.

Earnings Recap

Generate a post-earnings analysis for any stock using Yahoo Finance data.

What it does

• Shows the EPS beat/miss result with surprise percentage
• Presents quarterly financial trends (revenue, margins, EPS) over the last 4 quarters
• Calculates the stock price reaction on earnings day
• Compares the reaction to the stock's average earnings-day move
• Provides context on margin trends and revenue growth trajectory

Triggers

AAPL earnings recap, how did TSLA earnings go, MSFT earnings results, did NVDA beat earnings, post-earnings analysis, earnings surprise, what happened with GOOGL earnings, earnings reaction, stock moved after earnings, earnings report summary, EPS beat or miss, quarterly results, AMZN reported last night

Prerequisites

• Python 3.8+
• yfinance (auto-installed if missing)

Platform

All platforms (Claude Code, Claude.ai, other agents)

Setup

No setup required — yfinance pulls data from Yahoo Finance without authentication.

Reference Files

• references/api_reference.md — yfinance API reference for earnings history and financial statement methods

Earnings Recap — yfinance API Reference

Detailed reference for the yfinance methods used by the earnings-recap skill.

---

Earnings History

ticker.earnings_history

Returns a DataFrame with the last 4 quarters of actual vs estimated earnings:

Columns:

• epsEstimate — consensus EPS estimate at the time of reporting
• epsActual — reported EPS
• epsDifference — actual minus estimate
• surprisePercent — surprise as a percentage (decimal form: 0.037 = 3.7%)

Index is datetime of each earnings report date.

Usage for recap: The most recent row (index[0]) is the latest earnings report. Use this as the primary data point for the recap.

---

Quarterly Financial Statements

Income Statement

ticker.quarterly_income_stmt

Returns a DataFrame with financial line items as rows and quarter-end dates as columns (most recent first).

Key rows for earnings recap:

• Total Revenue — top-line revenue
• Cost Of Revenue — COGS
• Gross Profit — revenue minus COGS
• Operating Income — EBIT
• Net Income — bottom line
• Basic EPS — earnings per share (basic)
• Diluted EPS — earnings per share (diluted)
• EBITDA — if available

Margin calculations:

gross_margin = df.loc['Gross Profit'] / df.loc['Total Revenue']
operating_margin = df.loc['Operating Income'] / df.loc['Total Revenue']
net_margin = df.loc['Net Income'] / df.loc['Total Revenue']

YoY Growth:

# Columns are ordered most-recent-first
# Column 0 = latest quarter, Column 4 = same quarter last year (if available)
# Match by quarter (e.g., Q3 2024 vs Q3 2023)
revenue = df.loc['Total Revenue']
yoy_growth = (revenue.iloc[0] - revenue.iloc[3]) / abs(revenue.iloc[3])

Note: Column indexing depends on how many quarters are returned. Typically 4-5 quarters are available.

Cash Flow Statement

ticker.quarterly_cashflow

Key rows:

• Operating Cash Flow — cash from operations
• Capital Expenditure — capex
• Free Cash Flow — OCF minus capex

Balance Sheet

ticker.quarterly_balance_sheet

Key rows:

• Total Assets
• Total Debt
• Cash And Cash Equivalents
• Total Stockholders Equity

---

Historical Prices

# Around earnings date
from datetime import timedelta
hist = ticker.history(
    start=earnings_date - timedelta(days=10),
    end=earnings_date + timedelta(days=10)
)

Returns DataFrame with: Open, High, Low, Close, Volume.

Price reaction calculation tips:

• After-hours reporters: compare prior day's Close to next day's Open (gap) and next day's Close (full reaction)
• Before-market reporters: compare prior day's Close to same day's Close
• The biggest single-day |%change| near the earnings date is usually the reaction day
• Volume spike confirms the reaction day

---

Company Info

ticker.info

Key fields for context:

• shortName — company name
• sector, industry
• marketCap
• currentPrice, previousClose
• forwardPE, trailingPE
• fiftyTwoWeekHigh, fiftyTwoWeekLow

---

News

ticker.news

Returns a list of dicts:

• title — headline
• link — URL
• publisher — source name
• providerPublishTime — unix timestamp

Filter for recent news around the earnings date for earnings-related headlines.

---

Recommendations

ticker.recommendations

Returns a DataFrame with columns: strongBuy, buy, hold, sell, strongSell.

Use the most recent row to show current analyst sentiment distribution. Compare to the prior period to detect any post-earnings sentiment shifts.

---

Error Handling

try:
    hist = ticker.earnings_history
    if hist is None or (hasattr(hist, 'empty') and hist.empty):
        print("No earnings history — ticker may not have reported recently")
except Exception as e:
    print(f"Error: {e}")

Common issues:

• No earnings history: Company hasn't reported yet, or it's an ETF/fund
• Missing financial statement rows: Not all companies report the same line items; check with .loc and handle KeyError
• Quarterly alignment: Q-end dates in financial statements don't always align perfectly with calendar quarters; use the dates as-is from yfinance