aris-analyze-results

Analyze ML experiment results and generate comparison tables with statistical insights.

1.1k|116|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-analyze-results
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aris-analyze-results
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/aris-analyze-results
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-analyze-results

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Interpreting raw machine learning experiment outputs scattered across JSON and CSV files is tedious and error-prone, making it hard to compare runs, compute deltas against baselines, and draw defensible conclusions.

Core Features & Use Cases

  • Result Aggregation: Locates and parses JSON/CSV result files from figures/, results/, or project output directories into structured data.
  • Comparison Tables: Organizes results by independent variables (model type, hyperparameters, data config) and dependent metrics, always computing delta versus baseline.
  • Statistical Analysis: Reports mean and standard deviation across seeds, identifies parameter sweep trends, and flags outliers or suspicious results.
  • Use Case: After running a learning-rate sweep with three seeds, ask the assistant to analyze the results directory and receive a comparison table, key findings with interpretations, and suggested follow-up experiments.

Quick Start

Analyze the experiment results in my results/ directory and compare them against the baseline model.

Frequently Asked Questions about aris-analyze-results

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze ML experiment results across multiple runs?

Point the skill at your results directory and it locates all JSON and CSV files, parses them into structured data, and builds a comparison table organized by hyperparameters and metrics. It reports mean and standard deviation when multiple seeds are present.

How to compare experiment results against a baseline model?

The skill always computes delta versus baseline as part of its comparison table step. Results are organized by independent variables like model type and data config, with relative improvement shown for primary and secondary metrics.

What file formats does experiment result analysis support?

It parses JSON and CSV result files, searching common output locations such as figures/, results/, or project-specific output directories. Files are parsed into structured data before statistical analysis begins.

Can it detect outliers or suspicious experiment results?

Yes, the statistical analysis step flags outliers and suspicious results, checks reproducibility across seeds, and identifies trends in parameter sweeps such as monotonic, U-shaped, or plateau patterns.

What output does the experiment analysis produce?

Output includes a raw data table, numbered key findings with observation, interpretation, implication, and next step for each, plus suggested follow-up experiments. Significant findings can be drafted into project documentation updates.