skills.rest
Its-Atharva-Gupta
Its-Atharva-GuptaCOMMUNITY
Explore all skills by this author →
GitHub

plot-worker

Generates dual-axis learning curves and benchmark comparison charts from results.tsv files.

Updated Aug 28, 2026
Search Tags:#data visualization#plotting#publication figures#ml research#benchmark comparison#results.tsv#learning curves
One-click install
npx skills add https://github.com/Its-Atharva-Gupta/forge-researcher --skill plot-worker-its-atharva-gupta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: plot-worker
Source: https://github.com/Its-Atharva-Gupta/forge-researcher/tree/main/skills/plot_worker
Command: npx skills add https://github.com/Its-Atharva-Gupta/forge-researcher --skill plot-worker-its-atharva-gupta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning raw experiment results into publication-ready figures is repetitive and error-prone. This Skill converts a tab-separated results file into standardized learning curve and benchmark comparison plots without manual charting work. ## Core Features & Use Cases - Learning Curve Generation: Produces a dual-axis learning curve PNG from experiment metrics recorded in results.tsv. - Benchmark Comparison Charts: Creates a bar chart comparing results across models or configurations. - Use Case: After an evaluation worker finishes training runs and writes workspace/results.tsv, invoke this Skill to emit workspace/figures/learning_curve.png and workspace/figures/benchmark_comparison.png for inclusion in a research paper. ## Quick Start Generate publication plots from workspace/results.tsv into the workspace/figures directory.

Frequently Asked Questions about plot-worker

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

FAQPage Schema
How do I generate learning curves from experiment results?▼

Provide a results.tsv file containing your experiment metrics, then call the generate_publication_plots tool with the file path and an output directory. It produces a learning_curve.png visualizing metric progression across training steps or epochs.

How to create benchmark comparison charts for ML experiments?▼

Benchmark comparison charts are generated as bar charts from the same results.tsv input. The tool outputs benchmark_comparison.png, letting you visually compare performance across models, datasets, or hyperparameter configurations.

What input format does the plot generation require?▼

The input must be a tab-separated values file named results.tsv located in the workspace directory. The file should contain the experiment metrics produced by an upstream evaluation or training step.

What output files does the plotting step produce?▼

It produces two PNG artifacts in workspace/figures: learning_curve.png with dual-axis curves and benchmark_comparison.png with comparison bars. Both are intended to be publication-ready figures for manuscripts.

Why is no figure generated after running the plot step?▼

The most common cause is a missing or malformed workspace/results.tsv input file. Verify the evaluation worker completed successfully and wrote the results file before invoking the plotting tool.

Related Skills

Explore More Education & Research Skills→
Supporter09Supporter09

experiment-tracking-swanlab

Record metrics, configs, tags, and media for machine learning runs.

Community
Intermediate
GRIND-Lab-CoreGRIND-Lab-Core
100

paper-writing-pipeline

Automate paper writing from outline to LaTeX, PDF, and DOCX manuscripts.

Official
Advanced
debug-zhuweijiandebug-zhuweijian
13

results-analysis

Analyze ML experiment results into reports, statistics, and figure catalogs.

Community
Advanced
vuralserhat86vuralserhat86
43

data_visualization

Generate bar, line, and scatter visualizations from data using matplotlib and seaborn.

Community
Intermediate