mcpbeat Sign in

Financial Research Agent Skill

| Pull company financials, SEC filings, and analyst consensus for a public company. Use this skill whenever the user says "10-K", "10-Q", "earnings", "revenue of", "financials for", "analyst rating for", "price target for", or provides a stock ticker. Combines SEC EDGAR for official filings with Yahoo Finance / TipRanks for analyst data. Search + scrape only; no interact needed.

2k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1167
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/firecrawl/web-agent --skill financial-research

What comes with it

4 228 bytes besides the instruction
sites/sec-gov.md
sites/yahoo-finance.md

The instruction itself

7 sections, as written by the author

Financial Research

Extract official financials from SEC filings and cross-reference with analyst consensus. Public companies only.

When to use

  • User asks for a company's financials: "revenue of NVIDIA", "Apple's latest 10-K"
  • User asks for analyst sentiment: "what are analysts saying about TSLA?"
  • User provides a ticker with no clear verb: "MSFT" → assume they want a financial overview
  • User wants an earnings summary before or after a release

Do NOT use for private company research, crypto, or macro/market commentary — deep-research handles those better.

Strategy

  • Resolve the ticker.
  • User gave a ticker: use it directly.
  • User gave a company name: search "<company> stock ticker" and confirm from the top result.
  • Get the latest SEC filing.
  • Use the sec.gov playbook to locate the most recent 10-K (annual) or 10-Q (quarterly).
  • Scrape the filing index page, then the primary filing document.
  • Extract: revenue, net income, operating income, EPS (basic and diluted), gross margin, forward guidance if given.
  • Get analyst consensus.
  • Use the finance.yahoo.com playbook for the analyst tab.
  • Extract: consensus rating, average / low / high price target, number of analysts covering.
  • Cross-reference.
  • If the user asked for a specific metric, verify it against at least two sources.
  • Flag discrepancies between the filing and third-party aggregators.
  • Call formatOutput with the structured result.

Quick start

// Full financial overview
await agent.run({
  prompt: 'Get a complete financial overview of NVIDIA',
  skills: ['financial-research'],
  format: 'json',
})
// Specific metric
await agent.run({
  prompt: 'What was AAPL revenue in the most recent quarter?',
  skills: ['financial-research'],
})
// Earnings preparation for multiple tickers — delegate per-ticker
await agent.run({
  prompt: 'Get the latest reported revenue, EPS, and guidance for NVDA, AMD, and INTC',
  skills: ['financial-research'],
  format: 'json',
})

Output schema

{
  "ticker": "NVDA",
  "company": "NVIDIA Corporation",
  "fiscalPeriod": "FY2026 Q4 ended 2026-01-26",
  "filing": {
    "type": "10-K",
    "url": "https://www.sec.gov/...",
    "filedDate": "2026-02-21"
  },
  "financials": {
    "revenue": null,
    "netIncome": null,
    "operatingIncome": null,
    "epsBasic": null,
    "epsDiluted": null,
    "grossMargin": null,
    "unit": "USD millions"
  },
  "guidance": "",
  "analyst": {
    "rating": "Strong Buy",
    "priceTarget": { "average": null, "low": null, "high": null },
    "numAnalysts": null,
    "sourceUrl": ""
  },
  "sources": []
}

Tips

  • SEC EDGAR is the source of truth for the numbers. Yahoo and aggregators can lag or be wrong. If a number in the 10-K disagrees with Yahoo, trust EDGAR.
  • Watch the fiscal calendar. NVIDIA, Apple, and others don't use calendar quarters — always capture the exact fiscalPeriod the numbers apply to.
  • Units matter. SEC filings report in millions or thousands with a table-header note. Capture financials.unit so downstream consumers don't multiply by the wrong power of 10.
  • Don't fabricate analyst data. If Yahoo's analyst page 404s or loads empty, set analyst.rating to null and note it in sources. Never guess.
  • For earnings-release watches, include filing.filedDate so users can see if they're looking at yesterday's filing or last quarter's.

See also

  • deep-research — for qualitative research (moats, macro, competitive dynamics)
  • structured-extraction — lower-level helper for custom financial schemas
  • competitor-analysis — when comparing multiple public companies head-to-head

Other skills for the same job

different authors, same section of the catalogue
Invoice Organizer
by frostant
×5

Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.

3k tokens
Backtest Expert
by BaggaT236
×3

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

15k tokens scripts
Analyzing Financial Statements
by anthropics
vendor ×2

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

8k tokens scripts
Creating Financial Models
by anthropics
vendor ×2

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

8k tokens scripts
Earnings Calendar
by nicepkg
×2

This skill retrieves upcoming earnings announcements for US stocks using the Financial Modeling Prep (FMP) API. Use this when the user requests earnings calendar data, wants to know which companies are reporting earnings in the upcoming week, or needs a weekly earnings review. The skill focuses on mid-cap and above companies (over $2B market cap) that have significant market impact, organizing the data by date and timing in a clean markdown table format. Supports multiple environments (CLI, Desktop, Web) with flexible API key management.

17k tokens scripts
Agentic Wallet
by coinbase
vendor ×2

Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API calls, monetize an API, or query onchain data. Use whenever the user mentions signing in, login, authentication, wallet status, balance, address, sending money, paying someone, transferring tokens, ENS names, swapping/trading/converting tokens, funding/topping up/onramp, USDC, ETH, POL, SOL, the x402 bazaar, paid APIs, monetizing an endpoint, or querying onchain data on Base.

14k tokens
Alpha Vantage
by christophacham
×2

Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market news/sentiment, insider transactions, GDP, CPI, treasury yields, gold/silver/oil prices, Bitcoin/crypto prices, forex exchange rates, or calculating technical indicators (SMA, EMA, MACD, RSI, Bollinger Bands). Requires a free API key from alphavantage.co.

13k tokens
Braintree Automation
by christophacham
×2

Braintree Automation: manage payment processing via Stripe-compatible tools for customers, subscriptions, payment methods, and transactions

2k tokens needs MCP

How to use it

Copy the folder

Take firecrawl/financial-research from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.