shap
k-dense-ai
Understand which features drive your model's predictions.
Model interpretability
Machine learning & data science skills for AI agents
Data comes first here: analysis and visualisation Skills explore datasets, test hypotheses and build dashboards. Machine learning Skills fine-tune and evaluate models, train them across many GPUs and serve them, with smaller groups for computer vision, language and vector search.
Sort by
Most installed
532 Skills
Showing Skills in Machine learning & data science.- 1.8k
- 1.8k
dask
k-dense-ai
Scale your data workflows beyond available memory.
Scientific computing
- 1.8k
matlab
k-dense-ai
Reproducible numerical code for MATLAB and Octave.
Scientific computing
1.8kdeep-learning-pytorch
mindrally
Build deep learning models with sound practices.
Deep learning
+2
1.8khuggingface-vision-trainer
huggingface
Fine-tune vision models without a local GPU.
Computer vision
+1- 1.8k
optimize-for-gpu
k-dense-ai
GPU speedups checked for correctness and real performance.
Scientific computing
- 1.7k
torch-geometric
k-dense-ai
Build graph neural networks with practical PyG recipes.
Graph machine learning
- 1.7k
timesfm-forecasting
k-dense-ai
Forecast your time series without model training.
Time-series forecasting
- 1.7k
stable-baselines3
k-dense-ai
Train and test reinforcement learning agents.
Reinforcement learning
- 1.7k
simpy
k-dense-ai
Build queue simulations with reproducible results.
Simulation modeling
- 1.7k
pymoo
k-dense-ai
Find solutions and explore competing objectives.
Numerical optimization
- 1.7k
geomaster
k-dense-ai
Geospatial analyses with checks you can trace.
Geospatial analysis
+3 - 1.7k
pufferlib
k-dense-ai
Build PufferLib environments without API mix-ups.
Reinforcement learning
- 1.7k
huggingface-trackio
huggingface
Track training progress and diagnose troubled runs.
ML experiment tracking
+1 - 1.7k
vaex
k-dense-ai
Turn large scientific tables into checked insights.
Scientific data analysis
- 1.7k
deepchem
k-dense-ai
Molecular predictions with meaningful holdouts.
Molecular machine learning
1.7ksnowflake-dbt-airbnb-analytics
reason-machines
Turn Airbnb data into tested models and a dashboard.
Analytics engineering
1.7kfind-hidden-subdomains
useosint
Find forgotten hosts and the domains connected to them.
Attack surface mapping
- 1.7k
astropy
k-dense-ai
Work with astronomical data using Astropy.
Astronomical data analysis
- 1.7k
pyhealth
k-dense-ai
Build clinical prediction pipelines with checks that matter.
Clinical machine learning
+1 - 1.7k
torchdrug
k-dense-ai
Build graph-learning workflows with TorchDrug.
Scientific machine learning
- 1.7k
geopandas
k-dense-ai
More trustworthy results from your vector maps.
Geospatial analysis
- 1.7k
huggingface-community-evals
huggingface
Test models locally, starting with a smoke test.
Model evaluation
- 1.7k
molecular-dynamics
k-dense-ai
Explore molecular motion with simulations and analysis.
Molecular simulation
Yes, on hardware you provide or a cloud you connect. Training Skills set up the run, watch it, and save the evidence so results can be compared.
No, but the Skills show their working: which test they ran, on what data and with what assumptions, so you can judge the result.
Under Research & science, with the other domain-science Skills. This category keeps general data analysis and machine learning.