Interpret Curves
by rHedBull
Analyze training logs and explain what's happening. Use when reviewing training runs, understanding loss curves, or diagnosing completed training.
Skill Details
Repository Files
1 file in this skill directory
name: interpret-curves description: Analyze training logs and explain what's happening. Use when reviewing training runs, understanding loss curves, or diagnosing completed training.
Training Curve Analysis
Analyze existing training logs to understand what happened.
Step 1: Load Logs
Support CSV, JSON, TensorBoard, W&B, or pasted values
Step 2: Plot Overview
Loss curves (train/val), learning rate, gradient norm in 2x2 grid
Step 3: Detect Patterns
- Healthy training: steady decrease, train/val tracking, stable gradients
- Loss plateau: detect onset, duration, percentage of training
- Overfitting: detect onset, final gap
- Instability: coefficient of variation, severity
- Divergence: detect onset, preceding signals
Step 4: Statistical Summary
Overview stats, dynamics assessment, key metrics table, recommendations
Step 5: Compare Runs (if multiple)
Overlay plots, comparison table with final/best loss and timing
Related Skills
Attack Tree Construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Grafana Dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Matplotlib
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Scientific Visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
Seaborn
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Query Writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Scientific Visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.