Skill UI

Automates adapting pretrained models via transfer learning by analyzing requirements, generating PyTorch or TensorFlow fine-tuning code, validating data, tracking KPIs, and saving artifacts so you can quickly reuse existing models for new datasets and tasks.

A comprehensive skill for analyzing Non-Fungible Tokens (NFTs). It fetches collection metadata from APIs (like OpenSea), parses trait attributes, and calculates advanced rarity scores using multiple algorithms (e.g., rarity_score, information entropy). Use this tool to rank tokens by uniqueness, compare specific NFTs, or analyze the distribution of traits within an entire collection, outputting results in JSON or CSV format. Ideal for crypto research and market due diligence.

Automates Google BigQuery workflows via Rube MCP and Metabase, letting you run native SQL/MBQL queries, fetch metadata, and explore schemas before querying.

This skill provides comprehensive guidelines for monitoring Granola usage, tracking team meeting patterns, and building detailed analytics dashboards. It guides users in defining critical metrics (e.g., adoption rate, efficiency score) and establishing robust data pipelines. Users can stream meeting metadata from Granola to data warehouses like BigQuery, enabling deep, customizable reporting and automated weekly insights via services like Zapier and Slack.

Auto-activating skill guiding metadata extractor implementations within data pipelines, covering ETL, transformation, orchestration, and streaming best practices.

This skill provides comprehensive, structured audit logging for OpenRouter API interactions. It automatically captures essential metadata like total cost, token usage, model details, latency, and status, while also performing PII redaction. The resulting audit trail is stored in an append-only SQLite database, making it ideal for building compliance-ready systems, detailed cost monitoring, and deep debugging of production environments.

Enables efficient querying of the bioRxiv preprint server with keywords, authors, dates, and categories, returning structured JSON metadata and optional PDF downloads for literature reviews or tracking research trends.

Provides programmatic access to the CZ CELLxGENE Census (61M+ cells) for querying standardized single-cell expression, metadata, embeddings, and stats across tissues and diseases, supporting scanpy and ML workflows.

Automates detection and deep exploratory analysis across 200+ scientific data formats, assessing quality, extracting metadata, and recommending visualizations while generating markdown reports that guide downstream workflows and highlight structure and distributions.

FlowIO reads and writes Flow Cytometry Standard (FCS) files, exposing metadata, channels, and NumPy event arrays while allowing CSV/DataFrame conversion, making it ideal for cytometry pipelines and backend preprocessing services.

Query the NHGRI-EBI GWAS Catalog for SNP-trait associations, fetch study metadata, variant and trait details, and download summary statistics via the web or REST APIs to support genetic epidemiology and polygenic risk modeling.

Access aggregated OFR hedge fund time series and metadata without auth, covering Form PF stats, repo volumes, futures trader positioning, and leverage/counterparty metrics for risk monitoring or research.