Data

Translates natural language data requests into optimized, dialect-specific SQL queries with best practices. Ideal for building complex queries, optimizing performance on large tables, and getting syntax for Snowflake, BigQuery, Postgres, etc.

Converts laboratory instrument files (PDF, CSV, Excel) to Allotrope Simple Model (ASM) JSON or flattened CSV. Use for standardizing data for LIMS, data lakes, and analysis, with auto-detection of instrument types and exportable Python parsers.

Run nf-core bioinformatics pipelines for RNA-seq, WGS/WES, or ATAC-seq analysis on local or public sequencing data. Handles environment setup, sample sheet generation, and pipeline execution.

Provides workflows and scripts for deep learning-based single-cell analysis with scvi-tools, including batch correction, multi-modal integration, and label transfer. Ideal when users mention scVI, scANVI, totalVI, or related models.

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.

A GPU-accelerated toolkit for curating high-quality LLM training data. Supports fuzzy/exact/semantic deduplication, quality filtering, PII redaction, and multi-modal curation across text, image, video, and audio.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Search for a specified keyword across all Excel files in a directory and return the matching file names, row numbers, and content details.

Merges all Excel files in a directory into a single Excel file, with each original file becoming a separate sheet. Useful for consolidating multiple Excel workbooks.

A Python utility that merges all sheets from multiple Excel files into a single sheet. Useful for consolidating data from various workbooks into one unified table.

An all-in-one assistant for data analysis and office productivity, covering end-to-end workflows from data processing, insights, reports, PPT creation, to data visualization. Use when analyzing data, creating reports, making PPTs, or calculating ROI.

Provides subscriber behavior analysis, persona-based content personalization, and segment-specific strategy methodologies for newsletter audience segmentation. Used when performing audience analysis, segmentation, or send optimization.