Aldous - Statistical Application Code Generator AI Agent - slide 1
Aldous - Statistical Application Code Generator AI Agent - slide 2
Aldous - Statistical Application Code Generator AI Agent - slide 3
Aldous - Statistical Application Code Generator AI Agent - slide 4

AI-agentClaude-skills voor data-analisten

Aldous - Statistical Application Code Generator AI Agent

Turns your analysis plan into reproducible R or Python scripts with checks and a README.

$14.99· één bestand, van jou om te houden

Van jou om te houden · direct downloaden

All-in-one

Of allemaal, $6.99/mnd

Aldous en 2.500+ andere specialisten, in je AI. Vraag ze allemaal bij naam.

Abonneren · $6.99/maand

7 dagen gratis, daarna $6.99/mnd · altijd opzegbaar

  • Visa
  • Mastercard
  • American Express
  • Apple Pay

30 dagen geld terug · veilig afrekenen via Stripe

Lees de eerste regels
# Aldous - Statistical Application Code Generator

## Role

You are Aldous, a statistical programmer who has spent years turning analysis plans into scripts that another analyst can open, read, run and trust. You write in R (tidyverse style by default) or Python (pandas, statsmodels, scipy). You do not choose the science for the user. You take a written analysis spec, code it faithfully, make the assumptions visible, and make the run reproducible.

You work as an agent: plan the whole job first, then produce files in a fixed order, and use whatever tools the AI app gives you (code execution, file output, a data file the user uploads). If you can run code, you run it on the user's data or on a small synthetic example and report the real output. If you cannot, you say so in one line and deliver the scripts unrun, with an expected-output description instead of invented numbers.

## How you differ from Leila (general data scientist persona)

- **A general data scientist persona** talks through modelling choices, explores data and suggests approaches. It answers "what should I do with this data?"
- **You (Aldous)** answer "here is my plan, write the code." Your input is a spec: question, variables, methods. Your output is a script set (data prep, models, checks, tables, README) that implements that spec line by line and flags every place the spec was silent. If the user has no plan yet, point them to the data scientist persona first, then come back with a spec.

AI-agent · 109 regels · de eerste 12 getoond

Zo werkt het

  1. Koop of abonneerLeg het bestand voor $14.99 in je winkelwagen en het is van jou. Of abonneer: elk bestand in de winkel voor $6.99/mnd.
  2. Open in je AIDownload het bestand en plak het in je AI-chat of in een project. Abonnees koppelen in plaats daarvan één keer hun AI:

    Claude

    De AI-chat van Anthropic, op het web, desktop en telefoon · ongeveer 3 minuten

    Werkt op elk Claude-plan, ook Free.

    • Team- of Enterprise-plan: de workspace-owner voegt hem één keer toe in de organisatie-instellingen, daarna klikt iedereen op Connect.
    • Gebeurt er niets als je op Connect klikt? Sta pop-ups toe voor claude.ai en probeer het opnieuw.

    Op een telefoon? Stel het één keer in op een computer. Daarna verschijnt het vanzelf in de Claude-app op je telefoon. Mail me de link

    Nadat je een bestand hebt gekocht
    1. Download je .skill-bestand uit de bestelmail of vanuit je account.

    2. Zet in Claude code-uitvoering aan onder Settings › Capabilities en ga dan naar Customize › Skills › + › Create skill › Upload a skill.

    3. Begin een nieuwe chat en vraag bij naam om de specialist.

    Open de volledige gids

  3. Vraag bij naamStart een chat en vraag bij naam om Aldous. Het werkt vanaf het eerste bericht als die specialist.

Wat erin zit

  • aldous-statistical-application-code-generator.skillAI-agent · 109 regels · direct downloaden
  • Spec restated first, every assumption marked so nothing is hidden
  • R (tidyverse) or Python (statsmodels, scipy) scripts that run top to bottom
  • Assumption checks coded for the method you chose, never swapped silently
  • Honest run status: real output or clearly labelled not run

Dit doet je AI

Bekijk een echt voorbeeld
Jij vraagt

Spec: two-arm RCT, outcome systolic BP at week 12, covariates baseline SBP and age, alpha 0.05, complete case. Data dictionary below. Write the R scripts and a table for the paper.

Je AI antwoordt

You get: a restated spec with ASSUMED and SPEC NEEDED markers → a file tree → cleaning, descriptives, ANCOVA and diagnostics scripts with fixed seed and relative paths → a tidy results table with 95 percent CI → a README with defaults and limits → a run status line that says not run if nothing was executed → and up to 5 open questions ranked by impact.

// faq

Vragen voor je koopt

What does Aldous - Statistical Application Code Generator do?+

Aldous is an AI agent for Claude or ChatGPT that turns a statistical analysis spec into runnable R or Python code. He restates your plan, builds a file set for cleaning, descriptives, models, assumption checks and tables, sets seeds and relative paths, and writes a README. He covers common tests and models and reports honestly whether anything was actually run.

How is Aldous different from the Leila data scientist persona?+

Leila is a general data scientist persona for exploring data and discussing which approach to take. Aldous starts after that decision. His input is a written spec with variables and methods, and his output is a script set that implements it line by line, flags every place the spec was silent and keeps the run reproducible. Use Leila to choose, Aldous to code.

Will Aldous run the analysis and give me results?+

Only if your AI app has a code execution tool and you provide data. In that case he runs the scripts and shows the real log. Otherwise he labels the output not run and describes what each file will contain. He never fills in invented estimates or p-values, and he does not interpret significance for you.

Is this a replacement for a statistician?+

No. Aldous is programming help. He codes the standard checks for the method you name and flags designs that need a statistician, such as clustered data with few clusters, small samples or heavy missingness. For clinical, regulatory or high-stakes work, have a qualified statistician validate the plan and the code.

Hoe open ik het?+

Download je .skill-bestand uit de bestelmail of vanuit je account. Zet in Claude code-uitvoering aan onder Settings › Capabilities en ga dan naar Customize › Skills › + › Create skill › Upload a skill. Begin een nieuwe chat en vraag bij naam om de specialist.

Gebruik je ChatGPT, Gemini of een andere AI? Zo werkt het