84 skills · sorted by relevance
Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. Use for tabular data in RAM (1–100 GB) when pandas is too slow. Expression API: select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection pushdown. Reads CSV, Parquet, JSON, Excel, DBs, cloud. Larger-than-RAM: Dask; GPU: cuDF.
The English summary is being prepared. Showing the original description.
Out-of-core DataFrame for billion-row data via lazy evaluation and memory-mapped files. Use when data exceeds RAM (10 GB–TB) for fast aggregation, filtering, virtual columns, and visualization without loading. Supports HDF5, Arrow, Parquet, CSV with cloud (S3, GCS, Azure). Built-in ML transformers (scaling, PCA, K-means). In-memory: polars; distributed: dask.
The English summary is being prepared. Showing the original description.
Use when dataframe code is slow or runs out of memory, when data outgrows pandas, or when writing pandas 3, Polars or DuckDB code — vectorisation, dtypes, Copy-on-Write, lazy and out-of-core execution, and measuring before and after
The English summary is being prepared. Showing the original description.
Use when reading from or writing to Neo4j with Apache Spark or Databricks using the Neo4j Connector for Apache Spark 6.0 (org.neo4j.connectors:spark) or 5.x (org.neo4j:neo4j-connector-apache-spark). Covers SparkSession setup, DataFrame reads via labels/Cypher/relationship scan, DataFrame writes with SaveMode, node.keys for MERGE, relationship write mapping, partition and batch tuning, PySpark and Scala examples, Databricks cluster config, Databricks secrets for credentials, Delta Lake to Neo4j pipelines. Does NOT handle Cypher authoring — use neo4j-cypher-skill. Does NOT handle the Python bolt driver — use neo4j-driver-python-skill. Does NOT handle GDS algorithms — use neo4j-gds-skill.
The English summary is being prepared. Showing the original description.
Use this when performing DataFrame operations — including loading, filtering, joining, aggregating, transforming, or reshaping tabular data with polars or pandas.
The English summary is being prepared. Showing the original description.
Filter rows of a Datagrok DataFrame via the datagrok_exec tool through the Filters panel — by range, equals/contains/in-set, multi-value, boolean, free-text row expressions, or substructure (SMILES / SMARTS / molblock). Also covers clearing, inverting, the show-only-filtered vs destructive-drop split, and the filter event lifecycle (onRowsFiltering / onFilterChanged / onRowsFiltered). Use whenever the user says "filter", "show only", "hide rows where", "narrow to subset", "find rows that", "contains", "substructure search", "categorical filter", "range filter", "invert", "clear the filter", "clear filters", "drop rows", or asks for the filtered subset as a new table. Does NOT cover selection (separate skill) or generic DataFrame cloning (datagrok-df-and-columns).
The English summary is being prepared. Showing the original description.
Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when writing BigFrames code or doing pandas-style dataframe/ML work against BigQuery (e.g. in a notebook). Don't use for SQL-first workflows or the google-cloud-bigquery client library — use bigquery-basics.
The English summary is being prepared. Showing the original description.
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
The English summary is being prepared. Showing the original description.
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
The English summary is being prepared. Showing the original description.
根据DataFrame中的日期字段创建季节字段，将月份映射为春夏秋冬。
The English summary is being prepared. Showing the original description.
Work with genomic regions in Polars tables to find overlaps, nearby regions, covered bases, and gaps. Read and write bioinformatics files, query data with SQL, and check coordinate conventions when joining datasets or migrating from bioframe.
Examine Zeek connection logs for regular callbacks that may indicate communication with an attacker’s control server. Use ZAT and Pandas to group connections, measure timing variation, and identify source and destination pairs for further investigation.
Turn spreadsheets, query results, or pasted data into clear Python charts. Get help choosing chart types, formatting labels and colors, and producing static images or interactive charts with hover details and zoom.
Extract text and data from images of charts, tables, interfaces, and diagrams using a vision model, an AI that reads images. Turn the results into structured tables, recreate charts, or export data to Excel and CSV.
Generate Python code to retrieve economic indicators and financial prices from sources including FRED, World Bank, BLS, OECD, IMF, and Yahoo Finance. Scripts include data cleaning, indicator documentation, and error handling for reusable datasets and updates.
Write and debug Python regressions with PyFixest using a reference for model formulas, estimation functions, and standard errors. It also covers extracting results, comparing models, and producing regression tables and plots, including models that account for group differences.
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
The English summary is being prepared. Showing the original description.
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series models (ARIMA, SARIMAX, VAR) use statsmodels; for time series classification/clustering use aeon.
The English summary is being prepared. Showing the original description.
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
The English summary is being prepared. Showing the original description.
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
The English summary is being prepared. Showing the original description.
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
The English summary is being prepared. Showing the original description.
Parse Flow Cytometry Standard (FCS) files v2.0–3.1 and extract events/metadata for preprocessing workflows (e.g., when you need NumPy arrays, channel info, or CSV/DataFrame export from cytometry files).
The English summary is being prepared. Showing the original description.
ALWAYS use this skill instead of the Read tool for PDF files. The Read tool cannot extract PDF tables properly. Use this skill when: (1) Reading ANY PDF file, (2) Extracting tables from PDFs, (3) Converting PDF tables to pandas DataFrames, (4) Processing multi-page PDFs
The English summary is being prepared. Showing the original description.
Parses, queries, converts, and extracts from GTF and GFF3 gene-model annotation files - walking the gene/transcript/exon/CDS hierarchy with gffutils (queryable SQLite DB), converting formats and extracting transcript/CDS/protein FASTA with gffread, slurping to dataframes with gtfparse/pyranges, and sanitizing malformed files with AGAT. Covers the 1-based-inclusive vs 0-based BED coordinate conversion (start-1 only), deriving implicit features (introns/UTRs/TSS), phase-not-frame, the stop-codon-in-or-out-of-CDS convention, and the chr1-vs-1 seqid and gene-ID-version mismatches that silently produce all-zero count matrices and dropped joins. Use when extracting features or sequences from an annotation, converting GTF<->GFF3 or GTF->BED, traversing the gene tree, or diagnosing a coordinate/provenance mismatch upstream of counting or DE.
The English summary is being prepared. Showing the original description.