result-generate

Name: result-generate
Availability: InStock
Author: UnaryLab

Convert experimental outputs into publication-quality figures and tables with statistics.

Updated Aug 23, 2026

Search Tags:#research #statistics #plotting #reproducibility #tables #figures #ablation

Ready to run

npx skills add https://github.com/UnaryLab/ai-for-research --skill result-generate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: result-generate
Source: https://github.com/UnaryLab/ai-for-research/tree/main/skills/result-generate
Command: npx skills add https://github.com/UnaryLab/ai-for-research --skill result-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents slow, error-prone manual plotting by transforming messy experimental outputs into publication-quality figures and tables with honest statistical analysis.

Core Features & Use Cases

Publication-standard exhibits with rigor: generates figures and tables suitable for papers, including correct aggregation across seeds/workloads and uncertainty reporting.
Honest comparisons and counter-story: normalizes to baselines appropriately, computes error bars / confidence intervals / significance, and surfaces the settings where your method weakens.
Reproducible regeneration: produces the script that regenerates each exhibit from committed data plus a result → exhibit → command map.

Quick Start

Use result-generate to convert your experiment outputs into the specific Figure 3 and Table 2 you want for your target venue.

Frequently Asked Questions about result-generate

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

FAQPage Schema

How do I generate publication-quality figures and tables from raw experimental outputs?▼

To generate publication-quality figures from raw experimental outputs, you can convert result directories, CSV, JSON, and log files into paper-ready exhibits with correct statistics, uncertainty reporting, and venue-tuned formatting.

How do I create reproducible scripts for regenerating ablation tables and learning curves?▼

Creating reproducible scripts for regenerating ablation tables and learning curves involves producing per-exhibit scripts alongside a result-to-exhibit command map, ensuring consistent regeneration from committed data.

How do I compute correct statistics and confidence intervals for scaling curve comparisons?▼

Computing correct statistics and confidence intervals for scaling curve comparisons requires aggregating results across seeds and workloads, normalizing to baselines, and honestly reporting variance and significance.

Can I build Nature-style multi-panel exhibits directly from CSV and JSON result logs?▼

Yes, you can build Nature-style multi-panel exhibits directly from CSV and JSON result logs by transforming messy experimental outputs into publication-standard figures with honest statistical analysis.

What is the best way to normalize experimental results to baselines and surface counter-stories?▼

The best way to normalize experimental results to baselines and surface counter-stories is to compute error bars and significance while automatically highlighting the specific settings where your method weakens.

Does this approach handle architecture speedups and efficiency breakdowns for research papers?▼

Yes, this approach handles architecture speedups and efficiency breakdowns by converting raw experimental outputs into publication-quality tables and figures tailored to your target venue's formatting requirements.