skills.rest
Tx1207
Tx1207COMMUNITY
Explore all skills by this author →
GitHub

results-analysis

Generate structured analysis bundles from ML experimental artifacts.

5|2|Updated Jul 2, 2026
Search Tags:#visualization#statistics#reproducibility#figures#results-analysis#ml-research#experimental-artifacts
One-click install
npx skills add https://github.com/Tx1207/hello-scholar --skill results-analysis-tx1207
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: results-analysis
Source: https://github.com/Tx1207/hello-scholar/tree/main/skills/research/results-analysis
Command: npx skills add https://github.com/Tx1207/hello-scholar --skill results-analysis-tx1207

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a strict, artifact-driven workflow for evaluating ML/AI experimental results, ensuring that conclusions are grounded in verifiable evidence rather than narrative summaries.

Core Features & Use Cases

  • Inventory and validate artifacts (metrics, logs, seeds, baselines, and ablations) to define the evidence base.
  • Generate real scientific figures and a structured analysis bundle (analysis-report.md, stats-appendix.md, figure-catalog.md) to support repeatable decision making.
  • Provide a narrative-free analysis workflow that clearly distinguishes observations, support, and boundary conditions, suitable for both internal reviews and formal reporting.

Quick Start

Prepare your experimental artifacts and run the analysis pipeline to produce a strict analysis bundle.

Frequently Asked Questions about results-analysis

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

FAQPage Schema
How do I generate reproducible figures and statistical reports from ML experiment artifacts?▼

Cross-run comparison evaluates ML experimental results by inventorying and validating metrics, logs, seeds, baselines, and ablations across multiple runs to define a verifiable evidence base for rigorous conclusions.

How do I compare ML experimental results across different seeds and baselines?▼

Cross-run comparison evaluates ML experimental results by inventorying and validating metrics, logs, seeds, baselines, and ablations across multiple runs to define a verifiable evidence base for rigorous conclusions.

What is the best way to ensure my experimental results analysis is narrative-free and artifact-centered?▼

Artifact-centered analysis enforces strict evaluation by distinguishing observations, support, and boundary conditions from narrative summaries, ensuring ML experiment conclusions are grounded in verifiable evidence and predefined artifact structures.

Does this results-analysis workflow require predefined artifact structures before running?▼

Yes, the workflow enforces predefined artifact structures and formal statistical reporting, requiring you to prepare experimental artifacts like metrics, logs, seeds, and ablations before running the analysis pipeline.

What files are included in the structured analysis bundle for ML research?▼

The structured analysis bundle includes analysis-report.md, stats-appendix.md, and figure-catalog.md, which together provide verifiable analysis artifacts and clear documentation of blockers and limitations for repeatable decision making.

Related Skills

Explore More Education & Research Skills→
EmaRimoldiEmaRimoldi

experiment-design

Plan ML experiment designs into runnable plans with baselines and ablations.

Community
Advanced
Tx1207Tx1207
5

results-report

Consolidate post-analysis outputs into a decision-focused results report.

Community
Intermediate
tqLi99tqLi99
1

analyze-results

Compute statistics and comparison tables from experimental results.

Community
Advanced
siddsacharsiddsachar
1.4k

data_analyst

Analyze CSV and tabular datasets to generate statistical summaries, narratives, and charts.

Community
Advanced