Skip to content
Back to skills

Tabular Intelligence

ASecurity

Usar cuando se analizan datos tabulares (CSV, Excel, tablas, metricas). Triggers: 'analiza esta tabla', 'metricas del sprint', 'tendencia de', 'distribucion de', 'correlacion entre', 'KPIs', 'datos financieros', 'perfil estadistico', 'resumen de datos', 'outlier'.

  • 50 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 27, 2026
ai-agentspythongo

Works with

  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 28, 2026

npx -y skills add gonzalezpazmonica/savia --skill tabular-intelligence --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tabular Intelligence?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tabular Intelligence
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-tabular-intelligence/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-tabular-intelligence)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
layer: peripheral
name: tabular-intelligence
description: "Usar cuando se analizan datos tabulares (CSV, Excel, tablas, metricas). Triggers: 'analiza esta tabla', 'metricas del sprint', 'tendencia de', 'distribucion de', 'correlacion entre', 'KPIs', 'datos financieros', 'perfil estadistico', 'resumen de datos', 'outlier'."
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.category: analysis
  savia.context: project
  savia.maturity: beta
  savia.priority: high
  savia.tags: "tabular, datos, estadistica, analytics, csv, excel, perfil, metricas"
---

# tabular-intelligence

Analisis estadistico de datos tabulares sin pasar datos crudos al LLM.

## Pipeline

1. DETECT: identificar datos tabulares en el prompt (>5 filas)
2. EXTRACT: extraer a estructura columnar via tabular-profile.py
3. ANALYZE: computar perfil estadistico (media, std, quartiles, outliers, tendencia)
4. SUMMARIZE: generar resumen compacto (< 200 tokens)
5. REASON: el LLM interpreta el perfil, no los datos brutos

## Principios

- Zero-training: sin modelos, sin GPU, sin descargas
- Zero-hallucination: numeros exactos del computo
- Local-first: procesamiento local con Python/pandas

## Integracion

- MCP tool: tabular_query
- Self-audit: verifica uso de herramienta
- Agents: business-analyst, controlling-kpi, finance-*

Files in this skill

  • DOMAIN.md831 B
  • SKILL.md1.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…