analizar-mis-datos

analizar-mis-datos is a skill for Claude Code, Codex from gethouston/houston. It costs 126 tokens per session (2,041 once invoked), scanned A, original, MIT.

A Spanish-language data analysis assistant with three modes: experiment reports, anomaly checks, and data-quality audits. It uses statistical evidence and comparison baselines to explain what the data supports.

In plain words
What is it for?
Evaluating A/B tests, checking lift and confidence intervals, investigating unusual metric changes, and auditing tables in Postgres, BigQuery, Snowflake, or Redshift.
Why use it?
It prevents common analytical mistakes, such as calling a normal change an anomaly or recommending a product launch without statistical significance. It also records warnings when the data quality is limited.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Evaluating A/B tests, checking lift and confidence intervals, investigating unusual metric changes, and auditing tables in Postgres, BigQuery, Snowflake, or Redshift.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/analizar-mis-datos
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gethouston/houston --skill analizar-mis-datos
Clone the repo
git clone --depth 1 https://github.com/gethouston/houston

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for analizar-mis-datos

README.md
[![agentmods](https://agentmods.dev/badge/skills/gethouston/houston/analizar-mis-datos/github.svg)](https://agentmods.dev/skills/gethouston/houston/analizar-mis-datos)
Your own site
<a href="https://agentmods.dev/skills/gethouston/houston/analizar-mis-datos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/analizar-mis-datos/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for analizar-mis-datos

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/analizar-mis-datos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/analizar-mis-datos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.02041
Opus 5 $0.00063 $0.01020
Sonnet 5 $0.00025 $0.00408
Haiku 4.5 $0.00013 $0.00204

Measured 12d ago against content hash 515c88e0f892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

analizar-mis-datos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

store/agents-i18n/es/operations/.agents/skills/analizar-mis-datos/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analizar mis datos

Una sola primitiva analítica. Tres trabajos de datos: informes de experimentos, barridos de anomalías, auditorías de calidad de datos. Rigor por defecto: nunca recomiendo SHIP sin significancia, nunca declaro una anomalía sin línea base, nunca omito advertencias en los hallazgos de calidad de datos.

Cuándo usarla

  • subject=experiment - "analiza el test {X}" / "cómo le fue al experimento {Y}" / "informe del test A/B".
  • subject=anomaly - "hay algo raro en los datos hoy" / "revisión de anomalías" / "barrido diario de anomalías" / "por qué se disparó {métrica}".
  • subject=data-qa - "revisa la calidad de datos de {tabla}" / "por qué este número está mal" / "corre una auditoría de calidad en el almacén de datos".

Conexiones que necesito

Ejecuto el trabajo externo a través de Composio. Antes de correr esta habilidad verifico que las categorías de abajo estén conectadas. Si falta alguna, nombro la categoría, te pido conectarla desde la pestaña de Integraciones y me detengo.

  • Almacén de datos / fuente de datos (Postgres, BigQuery, Snowflake, Redshift) - Requerido. SQL de solo lectura para extraer variantes, líneas base de anomalías y chequeos de calidad.
  • Plataforma de experimentos (PostHog, Mixpanel, Amplitude) - Opcional. Se usa cuando subject=experiment y el test vive en una herramienta de analítica de producto. Si no hay ninguna conectada, trabajo con agregados que me pegues.

Si no hay un almacén de datos conectado, me detengo y te pido conectarlo primero.

Información que necesito

Primero leo tu contexto de operaciones. Por cada campo requerido que falte hago UNA pregunta en lenguaje simple (mejor modalidad: app conectada > archivo > URL > texto pegado) y espero.

  • Etapa de la empresa - Requerido. Por qué lo necesito: define valores por defecto sensatos para el tamaño de muestra y el efecto mínimo detectable en los experimentos. Si falta, pregunto: "¿Cómo describirías tu etapa ahora mismo: pre-lanzamiento, primeros usuarios, en crecimiento o estable?"
  • Dónde viven los datos de tu negocio - Requerido. Por qué lo necesito: tengo que saber a qué almacén de datos consultar. Si falta, pregunto: "¿Dónde viven los datos de tu negocio? Lo mejor es conectar tu almacén de datos desde la pestaña de Integraciones para que pueda leerlo directamente."
  • Qué estás midiendo ya - Requerido para subject=anomaly. Por qué lo necesito: barro las métricas que ya sigues y marco las desviaciones. Si falta, pregunto: "¿Qué números sigues más de cerca? Puedes listarlos o, mejor aún, conectar el dashboard donde viven."
  • Estructura de las tablas y expectativas de actualidad - Opcional para subject=data-qa. Por qué lo necesito: me ayuda a saber qué columnas no deberían ser nulas y qué tan desactualizada puede estar una tabla. Si no lo tienes, sigo adelante con TBD e infiero a partir de una muestra.

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 96 lines · 126 tokens per session scan A 515c88e0f892

Subscribe to this mod's changes

analizar-mis-datos is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 2,041 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens