results-analysis

Analyze experimental results data and generate markdown reports with statistical tests and figures.

Updated Aug 27, 2026

Search Tags:#analysis #visualization #statistics #ml #results #paper writing

Ready to run

npx skills add https://github.com/AnXueHua/auto-research --skill results-analysis-anxuehua

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: results-analysis
Source: https://github.com/AnXueHua/auto-research/tree/main/skills/results-analysis
Command: npx skills add https://github.com/AnXueHua/auto-research --skill results-analysis-anxuehua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides a systematic workflow for analyzing ML/AI experimental results and turning them into a polished Results section for research papers, ensuring statistical rigor and clear visualizations.

Core Features & Use Cases

Experimental Data Analysis: Load and validate CSV, JSON, TensorBoard logs, or Python pickle files.
Statistical Validation: Perform t-tests, ANOVA, Wilcoxon tests, and multiple‑comparison corrections.
Paper Content Generation: Produce markdown reports, figures, and draft text ready for inclusion in a manuscript.
Use Case: When a researcher asks to “analyze experimental results” or “create a results visualization”, this skill guides the entire process from data loading to quality check.

Quick Start

Ask the results-analysis skill to process 'experiments/results.csv' and generate a results draft.

Frequently Asked Questions about results-analysis

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

FAQPage Schema

How do I generate a paper-ready results section from experiment data?▼

To generate a paper-ready results section from experiment data, load CSV, JSON, TensorBoard logs, or pickle files for statistical validation, performance comparison, and visualization creation, outputting a markdown report draft.

Can I use TensorBoard logs for statistical validation in ML papers?▼

Yes, TensorBoard logs can be used for statistical validation in ML papers. The skill loads these logs alongside CSV, JSON, and pickle files to perform t-tests, ANOVA, and Wilcoxon tests for rigorous performance comparison.

What is the best way to compare machine learning model performance statistically?▼

The best way to compare ML model performance statistically is running t-tests, ANOVA, or Wilcoxon tests with multiple-comparison corrections. This validates experimental results and generates figures visualizing performance differences.

Does this workflow support creating visualizations from Python pickle files?▼

Yes, this workflow supports creating visualizations from Python pickle files. It loads pickle data, performs statistical analysis, and generates figures alongside a markdown report draft ready for manuscript inclusion.

How do I perform multiple-comparison corrections on ANOVA results?▼

To perform multiple-comparison corrections on ANOVA results, apply statistical validation procedures to your experimental data. The skill handles these corrections automatically to ensure rigor in ML paper results sections.

Are there limitations when analyzing TensorBoard logs for markdown reports?▼

A limitation when analyzing TensorBoard logs for markdown reports is ensuring data quality and proper loading. The skill requires structured experimental data to perform statistical tests and generate accurate figures and draft text.