Indec logo

Indec

Community
gauss314
indec

Datos macro y sociales de Argentina via la API oficial Series de Tiempo del Estado (apis.datos.gob.ar/series). ~4250 series del INDEC + BCRA + Min Economia + Sec Trabajo. Sin auth, sin API key. IPC nacional, EMAE, IPI, ISAC, EPH (desempleo), pobreza, comercio exterior, salarios (RIPTE, SMVM), tipo de cambio, reservas, REM expectativas. Transformaciones builtin (% YoY, % YTD, change) y agregacion temporal (daily→monthly→yearly) server-side. La API mas estable y mejor documentada del repo.

Overview

Publishergauss314
Repositoryskills
Skill nameindec
Stars
250
Forks
35
Bundled files
16
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.

  • 16 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 Indec 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/indec
  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/indec .claude/skills/indec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Indec 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 Indec 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 Indec 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.

INDEC Argentina — API Oficial de Series de Tiempo

Skill premium para extraer datos macroeconomicos y sociales de Argentina via la API oficial del Estado Argentino: apis.datos.gob.ar/series — sin API key, sin autenticacion, con documentacion oficial y politicas de no-break ABI.

A diferencia de skills basados en APIs internas (TradingView, Google Finance), esta es una API PUBLICA OFICIAL mantenida por la Direccion Nacional de Datos e Informacion Publica. Es la API mas estable y confiable de todo el repositorio.


🎯 Que datos cubre

~4,250 series totales del catalogo oficial, agregando datos de multiples organismos publicos argentinos:

OrganismoTipo de datos
INDECIPC nacional, IPC GBA, EMAE, IPI, ISAC, EPH (empleo/desempleo), pobreza, censos, comercio exterior, PIB
BCRATipo de cambio, reservas, REM expectativas, balance cambiario, tasas
Min EconomiaPIB cuentas nacionales, deuda publica, fiscal
Sec Trabajo (MTEySS)RIPTE, SMVM, haber jubilatorio
DGEYC (CABA)IPC Ciudad de Buenos Aires

🚀 Quick start

bash
# Snapshot rapido de la economia argentina
py scripts/fetch_indec.py snapshot --last 3

# IPC ultimos 12 meses
py scripts/fetch_indec.py ipc --last 12

# EMAE original + desestacionalizado
py scripts/fetch_indec.py emae --last 12

# Tipo de cambio diario → cierre mensual
py scripts/fetch_indec.py dolar --collapse month --aggregation end_of_period --last 12

# Buscar serie por keyword
py scripts/fetch_indec.py search "pobreza" --limit 10

# Serie por ID con transformacion (var YoY)
py scripts/fetch_indec.py series "145.3_INGNACUAL_DICI_M_38" --mode percent_change_a_year_ago --last 12

⚡ Lo unico que hace este skill

Tres killer features de esta API (no disponibles en otros skills del repo):

1. Transformaciones builtin server-side

Pedir inflacion interanual o acumulada YTD directamente desde el indice IPC, sin calcular cliente-side:

bash
# Inflacion interanual ya calculada
py scripts/fetch_indec.py series "<ID_IPC_INDICE>" --mode percent_change_a_year_ago

Modos disponibles: value, change, percent_change, percent_change_a_year_ago (inflacion YoY), percent_change_since_beginning_of_year (inflacion YTD), change_a_year_ago, change_since_beginning_of_year.

Ver references/REPRESENTATION_MODES.md.

2. Agregacion temporal builtin

Convertir serie diaria a mensual/anual directamente en el server:

bash
# Dolar diario → cierre mensual
py scripts/fetch_indec.py dolar --collapse month --aggregation end_of_period

Collapses: day, week, month, quarter, semester, year. Aggregations: avg, sum, end_of_period, min, max.

Ver references/COLLAPSE_AGGREGATIONS.md.

3. Multi-serie en una sola request

Combinar IPC + RIPTE + dolar en 1 request:

bash
py scripts/fetch_indec.py series "145.3_INGNACUAL_DICI_M_38,158.1_REPTE_0_0_5,168.1_T_CAMBIOR_D_0_0_26" --last 12

Estructura del skill

skills/indec/
├── SKILL.md                                # Este archivo
├── references/                             # 10 documentos exhaustivos
│   ├── REFERENCE.md                        # Overview general
│   ├── ENDPOINTS.md                        # Deep dive de los 4 endpoints
│   ├── PARAMS.md                           # Cada parametro explicado
│   ├── REPRESENTATION_MODES.md             # Las 7 transformaciones
│   ├── COLLAPSE_AGGREGATIONS.md            # Agregacion temporal
│   ├── SERIES_CATALOG.md                   # IDs canonicos por topico
│   ├── RESPONSE_FORMAT.md                  # Schema JSON / CSV completo
│   ├── DATA_SOURCES.md                     # Organismos publicadores
│   ├── COOKBOOK.md                         # 30+ recetas
│   └── LIMITATIONS_TROUBLESHOOTING.md      # Limites + errores comunes
├── assets/                                 # 5 archivos JSON
│   ├── known_series_ids.json               # Catalogo curado de IDs
│   ├── series_groups.json                  # Bundles pre-armados
│   ├── representation_modes.json           # Modes con ejemplos
│   ├── collapse_aggregations.json          # Aggregations con ejemplos
│   └── data_sources.json                   # Publicadores estructurados
└── scripts/
    └── fetch_indec.py                      # Script con 19 modos CLI

19 modos CLI disponibles

Consulta directa (4 modos)

ModoDescripcion
series IDSFetch por ID(s) — el modo mas potente
search QUERYBusca series por keywords
validate IDSValida que un ID sea correcto
dumpCatalogo completo (pesado, ~MBs)

Atajos por indicador (9 modos)

ModoQue devuelveIDs combinados
ipcIPC Nacional var mensual1 ID
ipc-completoIPC + nucleo + regulados + categorias5 IDs
emaeEMAE original + desestacionalizado2 IDs
salariosRIPTE + SMVM + haber jubilatorio5 IDs
comercioExportaciones totales (M/T/A)3 IDs
construccionISAC nivel general2 IDs
dolarTipo de cambio BNA diario1 ID (BCRA)
reservasReservas internacionales BCRA4 IDs (BCRA)
snapshotSnapshot macro Argentina5 IDs combinadas

Catalogos locales (5 modos)

ModoQue devuelve
catalogCatalogo curado de series IDs principales
groupsBundles pre-armados
sourcesOrganismos publicadores
modesRepresentation modes disponibles
aggregationsCollapse aggregations disponibles

Combinado (1 modo)

ModoQue devuelve
allSnapshot macro completo: IPC + EMAE + salarios + dolar + reservas + construccion + comercio

Flags principales

FlagDescripcion
--start YYYY-MM-DDFecha desde
--end YYYY-MM-DDFecha hasta
--last NUltimos N valores (⚠️ incompatible con sort/start/limit)
--mode XRepresentation mode (value / percent_change / percent_change_a_year_ago / etc.)
--collapse XAgregacion temporal (day/week/month/quarter/semester/year)
--aggregation XModo de agregacion (avg/sum/end_of_period/min/max)
--limit NDatapoints por serie (max 1000)
--offset NOffset para paginacion
--sort asc/descOrden
--metadata XVerbosidad (none/only/simple/full)
--format Xjson o csv
--rawResponse sin normalizar
-o fileGuardar a archivo
-qSilencioso

Diferencial vs bcra-macro y otros skills

Featureindecbcra-macroFRED
Sin auth✅✅❌ requiere key
Cobertura INDEC completa✅❌❌
Cobertura BCRA⚠️ subset✅ 638 series❌
Multi-organismo✅ INDEC + BCRA + Min Econ❌ solo BCRA✅ global
Transformaciones builtin (% YoY, YTD)✅ UNICO❌⚠️ requiere FRED transform
Agregacion temporal builtin✅ UNICO❌⚠️
Multi-serie en 1 request✅ UNICO❌❌
Documentacion oficial publica✅✅✅

Cuando usar indec vs bcra-macro:

  • INDEC (IPC, EMAE, EPH, PIB) → indec
  • Solo BCRA con cobertura completa → bcra-macro
  • Cruzar INDEC + BCRA en un dataset → indec

Casos de uso comunes

30+ recetas completas en references/COOKBOOK.md.

bash
# Inflacion mensual ultimos 12 meses
py scripts/fetch_indec.py ipc --last 12

# Inflacion interanual desde el indice
py scripts/fetch_indec.py series "<ID_IPC_INDICE>" --mode percent_change_a_year_ago

# Dolar diario → promedio mensual
py scripts/fetch_indec.py dolar --collapse month --aggregation avg

# Exportaciones totales por año
py scripts/fetch_indec.py series "75.3_IETG_0_M_31" --collapse year --aggregation sum --last 10

# Comparar IPC + RIPTE + Dolar (poder adquisitivo)
py scripts/fetch_indec.py series "145.3_INGNACUAL_DICI_M_38,158.1_REPTE_0_0_5,168.1_T_CAMBIOR_D_0_0_26" --last 12

# Snapshot macro
py scripts/fetch_indec.py snapshot --last 3

Documentacion completa

DocumentoContenido
references/REFERENCE.mdOverview general + arquitectura
references/ENDPOINTS.mdDeep dive de /series, /search, /dump, /validate
references/PARAMS.mdCada parametro con valores validos, defaults, ejemplos
references/REPRESENTATION_MODES.mdLas 7 transformaciones con ejemplos calculados
references/COLLAPSE_AGGREGATIONS.mdAgregacion temporal con casos de uso
references/SERIES_CATALOG.mdIDs canonicos organizados por topico
references/RESPONSE_FORMAT.mdSchema JSON / CSV completo
references/DATA_SOURCES.mdOrganismos publicadores con datasets
references/COOKBOOK.md30+ recetas listas para copy-paste
references/LIMITATIONS_TROUBLESHOOTING.mdLimites + errores comunes + debugging
assets/known_series_ids.jsonCatalogo curado de IDs
assets/series_groups.jsonBundles pre-armados por caso
assets/representation_modes.jsonModes con descripcion
assets/collapse_aggregations.jsonAggregations con casos
assets/data_sources.jsonPublicadores estructurados

⚠️ Limitaciones conocidas

Documentacion completa de limitaciones en references/LIMITATIONS_TROUBLESHOOTING.md.

Las mas importantes

  1. Maximo 1,000 datapoints por serie por request — para series muy largas, paginar con --offset.
  2. --last incompatible con --sort, --limit, --offset — el script lo maneja automaticamente.
  3. Multi-serie con frecuencias mezcladas — usar --collapse explicito para evitar surprises.
  4. Series DISCONTINUADAS marcadas como SERIE DISCONTINUADA en dataset.title — filtrarlas cliente-side.
  5. IDs criptos — no intentar adivinar, usar search o el catalogo curado.
  6. Lag del INDEC: IPC mensual aparece ~15 dias despues, PIB trimestral ~3 meses.

Por que esta API es MAS confiable que las demas

A diferencia de TradingView/Google Finance/BYMA (todas APIs internas):

Podes construir productos sobre esta API con muchisima mas confianza que sobre las APIs internas.


Referencias externas

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 Indec AI skill do?

Datos macro y sociales de Argentina via la API oficial Series de Tiempo del Estado (apis.datos.gob.ar/series). ~4250 series del INDEC + BCRA + Min Economia + Sec Trabajo. Sin auth, sin API key. IPC nacional, EMAE, IPI, ISAC, EPH (desempleo), pobreza, comercio exterior, salarios (RIPTE, SMVM), tipo de cambio, reservas, REM expectativas. Transformaciones builtin (% YoY, % YTD, change) y agregacion temporal (daily→monthly→yearly) server-side. La API mas estable y mejor documentada del repo.

Why use Indec on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gauss314/skills/tree/main/skills/indec. 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 Indec?

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 Indec?

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

Is the Indec 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 👇