Agent skill · data analytics · aradotso
high-stakes-analytics-decision-lab
Platform-neutral analytical skill that profiles messy data, selects case-adaptive methods, and produces source-backed visual reports for high-stakes decisions
Why this skill is useful
Adds a comprehensive analytical framework with adaptive routing and quality gates that the AI cannot generate on its own.
What it needs
Requires docker, python installed locally. About 7k tokens when loaded. Last updated 2026-08-05. 5 stars on the source repository.
What this skill does
High-Stakes Analytics & Decision Lab Skill by ara.so — Data Skills collection. A platform-neutral, evidence-constrained analytical system that transforms ambiguous questions into reproducible evidence products. It profiles data quality, selects case-adaptive analytical methods (descriptive, diagnostic, predictive, prescriptive), and produces source-backed reports with explicit uncertainty and claim boundaries. What It Does Instead of forcing every dataset through fixed pipelines, this system: Gates data quality before analysis (detects missing, duplicates, leakage, grain mismatches) Routes adaptively to descriptive, diagnostic, predictive, or prescriptive methods based on question + data Produces two-layer outputs: Evidence Intelligence Report (always) + Decision Intelligence Brief (conditional) Preserves lineage with hashed sources, reproducible transforms, and claim boundaries Handles shared uncertainty across alternatives (common market, time, operational shocks) Installation Quick Install (NPX) Manual Python Install Docker Core Architecture The system follows a fixed evidence spine with adaptive routing: Four Quality Gate Outcomes 1. ready — No material issues, continue 2. readywithdocumentedlimitations — Localized issues, visible limits 3. needsuserconfirmation — Requires explicit approval for cleaning actions 4. blocked — Critical failure, stop and request corrected data Four Analytical Routes 1. Descriptive — What is happening? (baseline, trends, distributions) 2. Diagnostic — Why? (drivers, decomposition, competing explanations) 3. Predictive — What next? (forecasts, validation, calibration, drift) 4. Prescriptive — What action? (alternatives, constraints, tail risk, sensitivity) Project Structure Configuration Create a config.yaml for your analysis: Usage Examples 1. Basic Evidence Analysis 2. Data Quality Profiling Only 3. Adaptive Route Selection 4. Predictive Route with Validation 5. Prescriptive Route with Shared Shocks 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/high-stakes-analytics-decision-lab