earnings-recap
Analyze a company's most recent (or a specified past) earnings report from Yahoo Finance data (yfinance): actual vs estimated EPS, surprise size, revenue and margin trends, and the stock's price reaction. Use this skill whenever the user asks how earnings went — beat or miss, earnings surprise, quarterly results, the post-earnings move, or an earnings call recap — including casual references to a past report such as "AMZN reported last night" or "how did they do". For an upcoming report, use earnings-preview.
- Installs
- 3.3K
- Last 24h
- +48
- Trending rank
- #3454
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/himself65/finance-skills --skill earnings-recap- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads earnings-recap automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Earnings Recap Skill
If your host has not already executed the shell probes below (for example, in Codex), run the commands inside the ! wrappers with its shell tool before choosing a setup path. Use the actual output; if shell access is unavailable, report that limitation.
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 "exec('try:\n import yfinance\n print(\'yfinance \' + yfinance.__version__ + \' installed\')\nexcept Exception:\n print(\'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
ticker = yf.Ticker("AAPL") # replace with actual ticker
# --- Earnings results ---
earnings_dates = ticker.get_earnings_dates(limit=12) # report timestamps, newest first
earnings_hist = ticker.earnings_history # last 4 quarters, indexed by fiscal quarter-end, oldest first
# --- Financial statements (about five quarters, newest first) ---
quarterly_income = ticker.quarterly_income_stmt
quarterly_cashflow = ticker.quarterly_cashflow
quarterly_balance = ticker.quarterly_balance_sheet
# --- Context ---
info = ticker.info
news = ticker.news
recommendations = ticker.recommendations
What to extract
| Data Source | Key Fields | Purpose |
|---|---|---|
get_earnings_dates() | Earnings Date, EPS Estimate, Reported EPS, Surprise(%) | Which report, when, and the beat/miss |
earnings_history | epsEstimate, epsActual, epsDifference, surprisePercent | Last four quarters' results by fiscal quarter |
quarterly_income_stmt | TotalRevenue, GrossProfit, OperatingIncome, NetIncome, BasicEPS | Actual financials |
history() | Daily closes around each report | Stock price reaction |
info | currentPrice, marketCap, forwardPE | Current context |
news | Recent headlines | Earnings-related news |
Step 3: Find the Report and Measure the Reaction
earnings_history is indexed by fiscal quarter-end, not by announcement date, so take report timing from get_earnings_dates(): the most recent report is the newest row with a Reported EPS. Its timestamp (US Eastern) sets the reaction window: at or after 16:00 means the company reported after the close; anything earlier means before the open or, occasionally, during the session. If the user asked about a specific quarter, use that row instead.
def earnings_reaction(ticker, report_ts):
"""% move from the last close before the report to the first close after it."""
daily = ticker.history(start=(report_ts - pd.Timedelta(days=10)).date(),
end=(report_ts + pd.Timedelta(days=10)).date())
closes = daily["Close"]
days = closes.index.date
d = report_ts.date()
if report_ts.hour >= 16: # reported after the close: report-day close -> next close
pre, post = closes[days <= d], closes[days > d]
else: # before the open or intraday: prior close -> report-day close
pre, post = closes[days < d], closes[days >= d]
if pre.empty or post.empty:
return None # the reaction session hasn't closed yet
return (post.iloc[0] / pre.iloc[-1] - 1) * 100
reported = earnings_dates[earnings_dates["Reported EPS"].notna()]
latest_ts = reported.index[0]
reaction_pct = earnings_reaction(ticker, latest_ts)
# Typical earnings-day move over the prior four reports
prior_moves = [earnings_reaction(ticker, ts) for ts in reported.index[1:5]]
avg_abs_move = pd.Series([abs(m) for m in prior_moves if m is not None]).mean()
If reaction_pct is None, the report came after the most recent close; say the regular-session reaction is still pending (an intraday history(..., prepost=True) call shows the after-hours move if the user wants it).
Step 4: Build the Earnings Recap
Cover these areas, leading with the result:
- Headline result — EPS actual vs estimate with the surprise %, revenue with year-over-year growth, and the stock's reaction.
- Estimates vs actuals — EPS estimate, actual, and surprise ($ and %) for the quarter in question.
- Quarterly trends — revenue, gross margin, operating margin, and EPS for the recent quarters, with margins computed from the statements (gross profit / revenue, operating income / revenue). yfinance usually returns about five quarters, so year-over-year growth is available for the latest quarter only (column 0 vs column 4); show sequential change for the others rather than inventing a comparison.
- Price reaction — the move in the reaction session, how it compares with the stock's average absolute earnings move over the prior four reports, and whether the stock has since held, given back, or extended the move.
- What changed — margin direction vs the prior quarter, any shift in the revenue growth trajectory, how this surprise compares with the company's usual pattern, and current analyst sentiment if available.
Step 5: Respond to the User
Open with the headline — which quarter, when it was reported, the beat or miss, revenue growth, and the reaction — then the supporting tables. Say what matters: whether this was a meaningful beat or a low bar cleared, and whether the trend is improving or deteriorating. Keep it factual and leave out investment recommendations.
Include the caveats that apply: Yahoo Finance data doesn't capture everything from the call (guidance, segment detail), revenue is compared year over year from the statements rather than against a revenue consensus, the price reaction can reflect a broader market move that day, and 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.
FAQ
What does the earnings-recap skill do?
Analyze a company's most recent (or a specified past) earnings report from Yahoo Finance data (yfinance): actual vs estimated EPS, surprise size, revenue and margin trends, and the stock's price reaction. Use this skill whenever the user asks how earnings went — beat or miss, earnings surprise, quarterly results, the post-earnings move, or an earnings call recap — including casual references to a past report such as "AMZN reported last night" or "how did they do". For an upcoming report, use earnings-preview.
How do I install earnings-recap?
Run npx skills add https://github.com/himself65/finance-skills --skill earnings-recap in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/earnings-recap/ (personal) or .claude/skills/earnings-recap/ (project).
Which AI agents can use earnings-recap?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is earnings-recap safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains earnings-recap?
It is published by himself65 in himself65/finance-skills. It has 3,254 recorded installs.
More from himself65/finance-skills
yfinance-data
himself65/finance-skills
Fetch financial and market data with the yfinance Python library (Yahoo Finance). Use this skill whenever the user wants stock data: current quotes and price history, financial statements (income statement, balance sheet, cash flow), options chains, dividends and splits, earnings and analyst estimates, price targets and ratings, institutional and insider holdings, news, multi-ticker comparisons, stock screens, or sector and industry data. Use it even when the user gives only a ticker symbol (AAPL, MSFT, TSLA) and the intent has to be inferred. For earnings previews or recaps, estimate revisions, valuation, correlation, liquidity, or ETF premium analysis, prefer the dedicated skill.
stock-correlation
himself65/finance-skills
Analyze how stocks move together using Yahoo Finance price history (yfinance): find correlated peers for a ticker, measure correlation, beta, and spread between specific tickers, cluster a group into a correlation matrix, and track rolling or regime-dependent correlation. Use this skill whenever the user asks what moves with a stock, what else drops when it drops, related tickers or sympathy plays, sector or supply-chain peers, pair trading or hedging pairs, beta or relative performance, correlation matrices, co-movement, or rolling/realized correlation — including well-known pairs like AMD/NVDA, GOOGL/AVGO, or LITE/COHR. With a single ticker, assume the user wants its correlated peers.
options-payoff
himself65/finance-skills
Render an interactive options payoff chart — expiry P&L plus Black-Scholes theoretical value — with sliders for strikes, premium, IV, DTE, and spot. Use this skill whenever the user describes or shares an options position or strategy and wants to see how it makes or loses money: vertical, calendar, diagonal, or ratio spreads, butterflies, condors and iron condors, straddles, strangles, covered calls, protective or naked puts, or any multi-leg structure. This includes pasted strikes, premiums, and expiries, requests like "show me the payoff" or "draw the P&L curve", and broker screenshots (IBKR, TastyTrade, Robinhood). Use it even when details are partial — defaults fill the gaps.
earnings-preview
himself65/finance-skills
Build a pre-earnings briefing for a stock from Yahoo Finance data (yfinance): the upcoming report date and timing, consensus EPS and revenue estimates with their range, the beat/miss track record, analyst ratings and price targets, and what to watch in the print. Use this skill whenever the user is preparing for an upcoming earnings report or asks what the street expects — consensus or whisper numbers, EPS expectations, whether a company will beat, an earnings setup, or an earnings-season preview — and whenever a ticker comes up in the context of upcoming earnings, even without the word "preview". For results that are already out, use earnings-recap.
generative-ui
himself65/finance-skills
Design system and templates for interactive HTML/SVG visuals in Claude and Codex, using an available inline renderer or a standalone HTML file. Use this skill whenever the user wants visual or interactive output rather than plain text or markdown: charts and dashboards, diagrams, flowcharts and architecture drawings, mockups, comparison grids, illustrations, interactive explainers ("explain how X works" with a visual), or tools with sliders, toggles, and live-updating displays — including financial data shown visually and requests phrased as "show me", "visualize", "draw", or "chart this".
hormuz-strait
himself65/finance-skills
Check the live status of the Strait of Hormuz from the Hormuz Strait Monitor dashboard: open, restricted, or closed status, tanker transits vs normal, stranded vessels, Brent price impact, war-risk insurance levels, cargo throughput, tanker freight rates, diplomatic developments, and global trade impact. Use this skill whenever the user asks about the Strait of Hormuz or the Persian Gulf in the context of oil, shipping, or geopolitical risk — whether Hormuz is open, chokepoint or transit disruption, Gulf tanker traffic, war-risk premiums, Middle East shipping routes, or energy supply-chain risk.
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown：查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件，或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.