Marketwatch logo

Marketwatch

Community
gauss314
marketwatch

Scraper de MarketWatch: quotes, financials (income/balance/cash flow), SEC filings, analyst estimates, options chain, historical OHLCV. Sin API key.

Overview

Publishergauss314
Repositoryskills
Skill namemarketwatch
Stars
250
Forks
35
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by gauss314 on GitHub. Read the source before you install it.

Installation

Install the Marketwatch AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/gauss314/skills/tree/main/skills/marketwatch
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/gauss314/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/marketwatch .claude/skills/marketwatch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Marketwatch in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Marketwatch on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Marketwatch is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MarketWatch — Financial Data Scraper

Scraper de MarketWatch que extrae quotes en tiempo real, financial statements (income, balance sheet, cash flow), SEC filings, analyst estimates, options chain y historical prices para acciones US y ADRs globales.

No requiere API key. Los datos se extraen del HTML de las páginas públicas.


⚠️ Aviso Legal

  • MarketWatch no tiene API pública oficial. Este scraper accede a datos públicamente disponibles en la web.
  • MarketWatch usa Datadome para protección anti-bot. El scraper utiliza headers de navegador completo para bypass.
  • Respetá los términos de servicio de MarketWatch.
  • Implementá rate limiting (mín 3 segundos entre requests, recomendado 5s).
  • El sitio puede cambiar su estructura HTML, rompiendo el scraper.

Instalación

bash
pip install requests beautifulsoup4

Scripts

ScriptDescripción
fetch_marketwatch.pyScript principal: todos los endpoints

Uso rápido

bash
# Quote + perfil de compañía
python scripts/fetch_marketwatch.py --ticker AAPL --quote --profile

# Income statement anual (por defecto)
python scripts/fetch_marketwatch.py --ticker MSFT --income

# Income statement trimestral
python scripts/fetch_marketwatch.py --ticker AAPL --income --quarterly

# Balance sheet + cash flow trimestral
python scripts/fetch_marketwatch.py --ticker NVDA --balance --cashflow --quarterly

# Todos los financials (income + balance + cashflow)
python scripts/fetch_marketwatch.py --ticker AAPL --financials

# SEC filings (10-K, 10-Q, 8-K)
python scripts/fetch_marketwatch.py --ticker AAPL --sec-filings

# Analyst estimates + target price
python scripts/fetch_marketwatch.py --ticker AAPL --analyst

# Options chain
python scripts/fetch_marketwatch.py --ticker AAPL --options

# Historical OHLCV
python scripts/fetch_marketwatch.py --ticker AAPL --historical

# Todo lo disponible
python scripts/fetch_marketwatch.py --ticker GGAL --all

# A JSON
python scripts/fetch_marketwatch.py --ticker AAPL --all --output aapl.json

# Control de rate limiting
python scripts/fetch_marketwatch.py --ticker AAPL --quote --delay 5

Endpoints disponibles

FlagDataFrecuenciaPeríodos
--quotePrecio, cambio, performance (5d, 1m, YTD)Tiempo real1 snapshot
--profileRatios clave, sector, industria, empleadosActual1 snapshot
--incomeIncome StatementAnual / Trimestral~5 años
--balanceBalance SheetAnual / Trimestral~5 años
--cashflowCash Flow StatementAnual / Trimestral~5 años
--financialsIncome + Balance + Cash Flow (atajo)Según --quarterly~5 años
--sec-filingsSEC filings (10-K, 10-Q, 8-K)Histórico~20+ entradas
--analystEstimaciones, target price, recomendacionesTrimestral/anual~15+ campos
--optionsOptions chain (calls/puts por strike)Fechas de expiraciónTodas disponibles
--historicalOHLCV histórico diarioDiario~1-3 meses
--allTodos los anterioresSegún --quarterly-

Datos disponibles por endpoint

Quote

Precio actual, cambio ($), cambio (%), Close anterior, y tabla de performance (5 Day, 1 Month, 3 Month, YTD, 1 Year).

Company Profile

Hasta 29 ratios financieros incluyendo: P/E Current, P/E Ratio, EPS, Market Cap, Shares Outstanding, Revenue/Employee, Employees, Dividend Yield, Beta, etc.

Financial Statements

Cada statement contiene ~40-60 items (Revenue, COGS, Gross Profit, Operating Income, Net Income, EBITDA, EPS, etc. para income; Cash, Receivables, Total Assets, Debt, Equity, etc. para balance sheet; Operating Cash Flow, Free Cash Flow, Capex, etc. para cash flow).

SEC Filings

Listado de filings con: Filing Date, Document Date, Type (10-K, 10-Q, 8-K), Category.

Analyst Estimates

Average Recommendation, Average Target Price, Number of Ratings, High/Median/Low target, Current/Next Year Estimates, y tabla de cambios de rating por firma.

Options

Options chain organizada por fecha de expiración con calls y puts, strikes, precios, volumen, open interest.

Historical

OHLCV diario con Date, Open, High, Low, Close, Volume (últimos ~60 días).


Protección anti-bot (Datadome)

MarketWatch usa Datadome para protegerse de scraping automatizado.

SituaciónSíntomaSolución
Muchos requests seguidos401 UnauthorizedAumentar --delay (mín 3s, ideal 5s)
IP bloqueada temporalmente401 incluso con delayEsperar 5-10 minutos
Headers incorrectos401 inmediatoUsar headers de navegador (ya incluidos)
Sin session cookies401El scraper maneja cookies automáticamente

Recomendación: No más de 4-5 endpoints por ticker por ejecución.


Estructura del skill

skills/marketwatch/
├── SKILL.md                              # Este archivo
├── references/
│   └── REFERENCE.md                      # Documentación completa de todos los endpoints
└── scripts/
    └── fetch_marketwatch.py              # Script principal

📖 Referencia completa: Para entender en detalle cada endpoint, columnas de options, campos de financials, estructura de historical data, etc., consultá references/REFERENCE.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Marketwatch AI skill do?

Scraper de MarketWatch: quotes, financials (income/balance/cash flow), SEC filings, analyst estimates, options chain, historical OHLCV. Sin API key.

Why use Marketwatch on TypingMind?

Because you install it once and use it with any model. Marketwatch is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Marketwatch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gauss314/skills/tree/main/skills/marketwatch. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Marketwatch?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Marketwatch?

As many as you like. As long as a model supports skills, you can use Marketwatch with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Marketwatch AI skill free?

Yes. It is published on GitHub by gauss314 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇