analyze-results

Parse JSON/CSV experiment results and compute metrics versus baseline.

Updated Mar 17, 2026

Search Tags:#insights #comparison #statistics #reproducibility #analyze #experiments #results

Ready to run

npx skills add https://github.com/loujc/Auto-claude-code-research-in-sleep-manual --skill analyze-results-loujc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: analyze-results
Source: https://github.com/loujc/Auto-claude-code-research-in-sleep-manual/tree/main/skills/analyze-results
Command: npx skills add https://github.com/loujc/Auto-claude-code-research-in-sleep-manual --skill analyze-results-loujc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the analysis of ML experiment results, turning raw outputs into structured data, comparison tables, and concise insights to accelerate data-driven decisions.

Core Features & Use Cases

Parse results from common outputs (JSON/CSV in folders like results/ figures/ or project-specific directories) into a structured dataset.
Build comparison tables across models, hyperparameters, data configurations, and report delta vs baseline.
Compute statistics & reveal insights including mean/std across seeds, reproducibility checks, trend identification, and outlier detection.
Use case: researchers run multiple experiments and get a ready-to-share summary with recommended next steps.

Quick Start

Run the analyze-results skill on your experiment directory to generate a summary table and insights.

Frequently Asked Questions about analyze-results

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

FAQPage Schema

How do I analyze ML experiment results from JSON and CSV files?▼

Analyzing ML experiment results involves parsing JSON and CSV files from directories like results/ or figures/ into structured data. The Skill compares metrics across models and hyperparameters, computes statistics across seeds, and generates concise summaries with recommended next steps.

What is the best way to compare model performance across different hyperparameters?▼

The best way to compare model performance is by building structured comparison tables that highlight deltas versus a baseline. This reveals trends and outliers across hyperparameters and data configurations, pairing observations with interpretations and actionable next steps.

How do I check reproducibility and compute statistics across multiple experiment seeds?▼

To check reproducibility across seeds, compute statistics like mean and standard deviation from your experiment results. The Skill parses raw output files to calculate these statistics, identify trends, detect outliers, and pair these observations with actionable interpretations.

Can I automatically generate project notes and recommended next steps from raw experiment outputs?▼

Yes, you can automatically generate project notes by parsing raw experiment outputs into structured insights. The Skill pairs observations with interpretations and recommended next steps, preparing a concise update suitable for sharing with project stakeholders.

Does this tool work with project-specific directories for parsing result files?▼

Yes, the tool identifies and parses JSON and CSV result files from both common output folders and project-specific directories. It loads these files into structured datasets to compare results across independent variables and compute primary metrics.