Google Finance logo

Google Finance

Community
gauss314
google-finance

Datos de Google Finance via batchexecute (API RPC interna sin auth ni API key). Quote, OHLC intraday 1-min y 5-min, OHLC daily, financials masivos (income/balance/cashflow), earnings, analyst recommendations + opinions, descripcion empresa, peers, news, indices globales (Dow/S&P/NASDAQ/VIX/DAX), sectors heatmap. Cobertura mercados US (NASDAQ/NYSE) y argentinos (BCBA). ⚠️ API NO oficial — leer LIMITATIONS_TROUBLESHOOTING.md antes de uso productivo.

Overview

Publishergauss314
Repositoryskills
Skill namegoogle-finance
Stars
250
Forks
35
Bundled files
9
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.

  • 9 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 Google Finance 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/google-finance
  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/google-finance .claude/skills/google-finance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Finance 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 Google Finance 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 Google Finance 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.

Google Finance — Data via API Interna sin Auth

Skill para extraer datos de Google Finance via su endpoint RPC interno batchexecute descubierto por reverse engineering — sin API key, sin autenticacion.

Cubre quote, OHLC historico (intraday 1-min / 5-min / daily / 6-meses), financials masivos, earnings, analyst recommendations con opinions individuales (Goldman, etc), descripcion empresa con address+employees, peers, news (con thumbnails), indices globales (Dow/S&P/NASDAQ/VIX/DAX/FTSE/Nikkei) y sectors heatmap.


⚠️ WARNINGS CRITICOS — LEER PRIMERO

Antes de usar este skill en cualquier escenario productivo, leer obligatoriamente references/LIMITATIONS_TROUBLESHOOTING.md.

TL;DR de los 4 warnings principales

  1. 🚨 API NO oficial — Google puede renombrar RPCs, cambiar layouts, agregar auth o cerrar el endpoint sin aviso.
  2. 🚨 Layouts SIN keys — Los responses son arrays posicionales. Si Google reordena campos, vas a leer mal sin error visible.
  3. 🚨 Rate limiting muy agresivo — > 5 req/s puede bloquear tu IP por horas. Recomendado: sleep ≥ 0.5s entre requests.
  4. 🚨 Sin warranty de continuidad — Si construis algo importante, tener fallback con otro provider (Yahoo Finance, TradingView, Finnhub).

Cuando NO usar este skill

  • Trading en produccion con decisiones criticas (usar feeds oficiales).
  • Aplicaciones publicas que sirvan los datos a usuarios.
  • Volumen > 10k requests/dia (riesgo de bloqueo permanente de IP).
  • Redistribuir los datos como propios (terminos de uso de Google).

Cuando SI usar este skill

  • Investigacion personal y prototipos.
  • Backtest con cache local.
  • Analisis comparativo cruzado con otros providers.
  • Casos donde los datos UNICOS de Google son criticos (intraday 1-min gratis, detalle individual de analyst opinions).

🚀 Quick start

bash
# Quote basico
py scripts/fetch_gfinance.py quote GGAL:NASDAQ
py scripts/fetch_gfinance.py quote AAPL:NASDAQ
py scripts/fetch_gfinance.py quote GGAL:BCBA       # mercado argentino

# Intraday del dia actual
py scripts/fetch_gfinance.py intraday-5min AAPL:NASDAQ
py scripts/fetch_gfinance.py intraday-1min GGAL:NASDAQ

# Daily historico
py scripts/fetch_gfinance.py daily-6m AAPL:NASDAQ

# Indices globales (Dow, S&P, NASDAQ, VIX, DAX, FTSE, Nikkei...)
py scripts/fetch_gfinance.py indices

# Analyst recommendations + opinions individuales
py scripts/fetch_gfinance.py analysts NVDA:NASDAQ

# Todo en uno (6 requests pipelinadas)
py scripts/fetch_gfinance.py all GGAL:NASDAQ

Estructura del skill

skills/google-finance/
├── SKILL.md                                # Este archivo
├── references/                             # 5 documentos
│   ├── REFERENCE.md                        # Overview general + batchexecute
│   ├── RPC_IDS.md                          # Catalogo de los 14+ RPC IDs
│   ├── RESPONSE_FORMAT.md                  # Parser deep dive del wrb.fr protocol
│   ├── LIMITATIONS_TROUBLESHOOTING.md      # ⚠️ Warnings, plan B, debugging
│   └── COOKBOOK.md                         # 25 recetas listas
├── assets/                                 # 3 archivos JSON
│   ├── rpc_ids.json                        # Catalogo estructurado de RPCs + args
│   ├── chunk_layouts.json                  # Layouts posicionales de los arrays
│   └── consent_cookies.json                # Cookies de bypass del consent
└── scripts/
    └── fetch_gfinance.py                   # Script principal — 19 modos CLI

19 modos CLI disponibles

Por simbolo

ModoDataRPC ID
quote SYMPrecio + change + currency + market hoursgCvqoe
quote-full SYMQuote + industry + market cap + volumedlNq8b
description SYMDescripcion + address + employees + ratios + URLsJL8oKc
peers SYMRelated stocks (default 4, controlable con --peers-count)SICF5d
analysts SYMRecommendations summary + opinions individualesYTM9q
earnings SYMEarnings history multi-periodXxQsbd
technicals SYMRatings tecnicos (similar a TradingView Recommend.*)gXxkFd
financials SYMIncome + balance + cashflow ~22 KB multi-periodPr8h2e
intraday-1min SYMOHLC 1-min del dia actual (~30 KB)c2u4wc
intraday-5min SYMOHLC 5-min con OHLC completo (~5 KB)c2u4wc
daily SYMOHLC diario ultimo mes (~22 dias)c2u4wc
daily-6m SYMOHLC diario ultimos ~6 mesesc2u4wc
news SYMNews especificas del simbolokA4MVd
news-related SYMNews globales (con related symbols del query)kA4MVd

Globales (sin simbolo)

ModoDataRPC ID
indicesIndices globales: Dow, S&P, NASDAQ, VIX, DAX, FTSE, Nikkei, etchgueg
sectorsSectors equity heatmap (Health Care, Tech, etc)vNewwe

Catalogos locales (sin HTTP)

ModoData
rpcsCatalogo de RPC IDs con args templates y descripciones
layoutsLayouts posicionales de los arrays anidados
cookiesCookies de bypass del consent screen

Combinado

ModoData
all SYMquote + description + analysts + financials + daily + news (6 requests)

Formato de simbolos

DondeFormatoEjemplos
Tickers USTICKER:NASDAQ o TICKER:NYSEAAPL:NASDAQ, JPM:NYSE
ADRs argentinasTICKER:NASDAQ o TICKER:NYSEGGAL:NASDAQ, BBAR:NYSE
Tickers BCBA (locales argentinas)TICKER:BCBAGGAL:BCBA, YPFD:BCBA
Brazil B3TICKER:BMFBOVESPAPETR4:BMFBOVESPA
Spain BMETICKER:BMESAN:BME
Germany XetraTICKER:XETRSAP:XETR
IndicesIDX:INDEXSP/DJX/NASDAQ/CBOE.INX:INDEXSP, .DJI:INDEXDJX

El script tambien acepta el orden invertido (NASDAQ:GGAL) — auto-detecta cual es el exchange. Pero el formato canonical de Google es TICKER:EXCHANGE.


Diferenciales unicos vs otros skills del repo

FeatureGoogle FinanceTradingViewYahooFinnhub
Sin auth✅✅✅Freemium
OHLC intraday 1-min publico gratis✅ UNICO❌ (paid)⚠️ limited⚠️ paid
OHLC 5-min completo✅❌⚠️⚠️
Indices globales en 1 call (Dow+S&P+NASDAQ+VIX+DAX+FTSE+Nikkei...)✅ UNICO⚠️ uno por uno⚠️⚠️
Detalle individual de analyst opinions (nombre, firm, target, fecha)✅ UNICO⚠️ solo agregado⚠️✅
Sectors heatmap✅⚠️❌❌
Descripcion empresa con address fisico + employees✅ UNICO⚠️⚠️✅
Quote delayed✅✅✅✅
Financials✅ (~22 KB)✅✅✅
News con thumbnails✅✅✅✅

Cuando usar Google Finance > TradingView

  • Necesitas OHLC intraday 1-min sin pagar.
  • Necesitas detalle individual de opinions por analista con firma/target/fecha.
  • Necesitas el address fisico de una empresa argentina.
  • Necesitas indices globales (Dow+S&P+NASDAQ+VIX+DAX+FTSE+Nikkei) en una sola call.

Cuando usar TradingView > Google Finance

  • Necesitas screener masivo con filtros tipo SQL.
  • Necesitas ISIN/CUSIP/CIK del simbolo (Symbol Search v3).
  • Necesitas indicadores tecnicos pre-calculados (RSI/MACD/EMAs/pivots).
  • Necesitas robustez — TV es mucho mas estable que Google Finance.

Consideraciones tecnicas

Endpoint

POST https://www.google.com/finance/beta/_/FinHubUi/data/batchexecute?rpcids={RPC_ID}

Headers requeridos

Ya configurados en el script:

python
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
    "Content-Type": "application/x-www-form-urlencoded;charset=UTF-8",
    "X-Same-Domain": "1",           # CRITICO
    "Origin": "https://www.google.com",
    "Referer": "https://www.google.com/finance/...",
}

Cookies de bypass

El script las pasa automaticamente:

python
COOKIES = {
    "CONSENT": "PENDING+999",
    "SOCS": "CAESHAgBEhJnd3NfMjAyNTAxMjMtMF9SQzMaAmVuIAEaBgiAvLW8Bg",
}

Si dejan de funcionar, ver LIMITATIONS_TROUBLESHOOTING.md seccion 6 para capturar cookies frescas.

Response format (wrb.fr)

Los responses usan el protocolo wrb.fr de Google (XSSI prefix + JSON serializado doble). El script tiene un parse_wrbfr() que lo maneja. Detalles en RESPONSE_FORMAT.md.

Rate limiting

⚠️ Aggressive. Recomendado:

  • Sleep ≥ 0.5s entre requests.
  • < 1k requests/dia para no triggear bloqueo IP.
  • NO usar desde CI sin precauciones (cloud IPs en blacklist).

Output

  • Por defecto: JSON al stdout.
  • -o archivo.json: guarda a archivo (UTF-8, ensure_ascii=False).
  • -q: modo silencioso (sin logs INFO).
  • --raw: retorna response raw sin extraer del array wrb.fr.

Manejo de errores

El script captura requests.HTTPError y muestra el body para debugging. Si el endpoint deja de funcionar, te apunta a LIMITATIONS_TROUBLESHOOTING.md.


Casos comunes — recetas rapidas

25 recetas completas en COOKBOOK.md.

bash
# Quote rapido
py scripts/fetch_gfinance.py quote GGAL:NASDAQ -q

# Stock argentino BCBA
py scripts/fetch_gfinance.py quote GGAL:BCBA -q

# Indices globales del dia
py scripts/fetch_gfinance.py indices -q

# Intraday 5-min con OHLC completo
py scripts/fetch_gfinance.py intraday-5min AAPL:NASDAQ -o aapl_5min.json

# Daily ultimos 6 meses
py scripts/fetch_gfinance.py daily-6m AAPL:NASDAQ -o aapl_6m.json

# Analyst recommendations + opinions individuales
py scripts/fetch_gfinance.py analysts NVDA:NASDAQ -q

# Comparar empresa con peers
py scripts/fetch_gfinance.py peers GGAL:NASDAQ --peers-count 5 -q

# Todo-en-uno (snapshot completo)
py scripts/fetch_gfinance.py all GGAL:NASDAQ -o ggal_complete.json

Documentacion completa

DocumentoContenido
references/REFERENCE.mdOverview general + batchexecute deep dive
references/RPC_IDS.mdCatalogo detallado de los 14+ RPC IDs con args + outputs
references/RESPONSE_FORMAT.mdParser deep dive del wrb.fr (XSSI, doble JSON, edge cases)
references/LIMITATIONS_TROUBLESHOOTING.md⚠️ Warnings, debugging, plan B con providers alternativos
references/COOKBOOK.md25 recetas listas para copy-paste
assets/rpc_ids.jsonCatalogo de RPCs con args templates y descripciones
assets/chunk_layouts.jsonLayouts posicionales de cada array (que indice = que campo)
assets/consent_cookies.jsonCookies de bypass del consent screen

Inspiracion y atribuciones

Este skill fue construido a partir de research del HTML de google.com/finance/beta/quote/GGAL:NASDAQ, identificando los chunks AF_initDataCallback con su sistema "Wiz" (mismo que usa Search, Maps, Translate). El protocolo wrb.fr es publico y bien documentado por la comunidad (no por Google).

Implementaciones similares en otros lenguajes:

  • google-finance-quotes (Node.js) — usa el mismo endpoint
  • mfinance (Python, distinto enfoque)
  • Multiples proyectos OSS de scraping de finance.google.com

Este skill se distingue por:

  1. 24 modos CLI sobre 14+ RPC IDs distintos.
  2. Documentacion exhaustiva de los warnings y plan B.
  3. Catalogo estructurado de RPCs + layouts posicionales en assets.
  4. Parser robusto del wrb.fr con manejo de todos los edge cases.

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 Google Finance AI skill do?

Datos de Google Finance via batchexecute (API RPC interna sin auth ni API key). Quote, OHLC intraday 1-min y 5-min, OHLC daily, financials masivos (income/balance/cashflow), earnings, analyst recommendations + opinions, descripcion empresa, peers, news, indices globales (Dow/S&P/NASDAQ/VIX/DAX), sectors heatmap. Cobertura mercados US (NASDAQ/NYSE) y argentinos (BCBA). ⚠️ API NO oficial — leer LIMITATIONS_TROUBLESHOOTING.md antes de uso productivo.

Why use Google Finance on TypingMind?

Because you install it once and use it with any model. Google Finance 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 Google Finance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gauss314/skills/tree/main/skills/google-finance. 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 Google Finance?

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 Google Finance?

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

Is the Google Finance 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 👇