“datasets”

INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets.

Returns two Apify datasets, files or Google Sheets by URL, or JSON arrays joined on key fields...

A dataset, train/test split, evaluation set, CSV or JSONL is supplied.

NCBI Datasets — the US National Library of Medicine's genome, gene and taxonomy reference service…

INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples.

Generates code that transforms datasets between ML schemas for model training or evaluation.

Helps users of the Timefold Employee Shift Scheduling (ESS) model understand an optimized schedule by fetching and interpreting the dataset via the API.

Version datasets with checksums, manifests, and semantic versioning.

Use this skill when designing, cleaning, deduplicating, or documenting datasets for model training and evaluation including schema design, class imbalance…

Helps users of the Timefold Field Service Routing (FSR) model understand an optimized route plan by fetching and interpreting the dataset via the API.

Helps users of the Timefold Pick-up and Delivery Routing (PDR) model understand an optimized route plan by fetching and interpreting the dataset via the API.

Define a self-contained, reusable Dataset component, including its source revision and the rules that derive usable inputs.

Clean, normalize, and prepare raw datasets for analysis or ML.

Discover startup founders and employees from the full parsed dataset, company website, web search and LinkedIn.

Curate generated images into a clean training dataset, validate metadata, remove duplicates, and sync manifests/assets to Hugging Face.

Create and manage datasets on Hugging Face Hub.

Tabular data retrieval.

Normalized official data with provenance, aggregations, insights, free samples and agent access.

Normalized official data with provenance, aggregations, insights, free samples and agent access.

Use when registering, validating, or documenting datasets for GapForge v0.6 experiment workspaces.

Write a manifest.json + traceability.json for a dataset.

INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples.

学术数据集发现与推荐，深度集成 awesome-public-datasets，覆盖 30+ 学科分类

Read-only discovery for 440 Malaysian public datasets with freshness, licence, and provenance.