Data & AI skills

Compare and implement eviction policies (LRU, LFU, FIFO, S3FIFO, ARC) for bounded-capacity caches. Use when choosing or implementing an eviction policy for a buffer pool, page cache, CDN edge, or LLM KV cache, or when writing a replay simulator that supports multiple policies. Clarifies recency vs frequency semantics, queue topology, saturating counters, ghost buffers, and the second-chance rule that distinguishes modern FIFO-family policies from classic LRU.

The English summary is being prepared. Showing the original description.

Fit first-order dynamic models to experimental step response data and extract K (gain) and tau (time constant) parameters.

The English summary is being prepared. Showing the original description.

Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric formats, and clean data quality issues. This skill should be used when you need to harmonize lab values from different sources, convert units for clinical analysis, fix formatting inconsistencies (scientific notation, decimal separators, whitespace), or prepare lab panels for research.

The English summary is being prepared. Showing the original description.

Preprocessing and cleaning techniques for astronomical light curves. Use when preparing light curve data for period analysis, including outlier removal, trend removal, flattening, and handling data quality flags. Works with lightkurve and general time series data.

The English summary is being prepared. Showing the original description.

Use scipy.optimize.curve_fit for nonlinear least squares parameter estimation from experimental data.

The English summary is being prepared. Showing the original description.

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality monitoring, and DataOps. Use when designing data architectures, building batch or streaming data pipelines, optimizing data workflows, or implementing data governance.

The English summary is being prepared. Showing the original description.

Matched filtering techniques for gravitational wave detection. Use when searching for signals in detector data using template waveforms, including both time-domain and frequency-domain approaches. Works with PyCBC for generating templates and performing matched filtering.

The English summary is being prepared. Showing the original description.

Download water level data from USGS using the dataretrieval package. Use when accessing real-time or historical streamflow data, downloading gage height or discharge measurements, or working with USGS station IDs.

The English summary is being prepared. Showing the original description.

Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.

The English summary is being prepared. Showing the original description.

Lomb-Scargle periodogram for finding periodic signals in unevenly sampled time series data. Use when analyzing light curves, radial velocity data, or any astronomical time series to detect periodic variations. Works for stellar rotation, pulsation, eclipsing binaries, and general periodic phenomena. Based on lightkurve library.

The English summary is being prepared. Showing the original description.

Detect flood events by comparing water levels to thresholds. Use when determining if flooding occurred, counting flood days, aggregating instantaneous data to daily values, or classifying flood severity.

The English summary is being prepared. Showing the original description.

Detect long-term trends in time series data using parametric and non-parametric methods. Use when determining if a variable shows statistically significant increase or decrease over time.

The English summary is being prepared. Showing the original description.

A toolkit for fuzzy string matching and data reconciliation. Useful for matching entity names (companies, people) across different datasets where spelling variations, typos, or formatting differences exist.

The English summary is being prepared. Showing the original description.

Data conditioning techniques for gravitational wave detector data. Use when preprocessing raw detector strain data before matched filtering, including high-pass filtering, resampling, removing filter wraparound artifacts, and estimating power spectral density (PSD). Works with PyCBC TimeSeries data.

The English summary is being prepared. Showing the original description.

Reduce dimensionality of multivariate data using PCA with varimax rotation. Use when you have many correlated variables and need to identify underlying factors or reduce collinearity.

The English summary is being prepared. Showing the original description.

High-performance numerical computing and machine learning workflows using JAX. Supports array operations, automatic differentiation, JIT compilation, RNN-style scans, map/reduce operations, and gradient computations. Ideal for scientific computing, ML models, and dynamic array transformations.

The English summary is being prepared. Showing the original description.

Guidance for analyzing network packet captures (PCAP files) and computing network statistics using Python, with tested utility functions.

The English summary is being prepared. Showing the original description.

An overview of the core data API of ObsPy, a Python framework for processing seismological data. It is useful for parsing common seismological file formats, or manipulating custom data into standard objects for downstream use cases such as ObsPy's signal processing routines or SeisBench's modeling API.

The English summary is being prepared. Showing the original description.

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

The English summary is being prepared. Showing the original description.

Power system network data formats and topology. Use when parsing bus, generator, and branch data for power flow analysis.

The English summary is being prepared. Showing the original description.

Use for parsing structured unit commitment input data from JSON, CSV, benchmark cases, spreadsheets, databases, or nested tables; finding fields for time periods, resources, load, reserve, generator limits, initial conditions, startup data, renewable availability, and production costs without assuming one source-specific schema.

The English summary is being prepared. Showing the original description.

Tools and techniques for detrending time series data in macroeconomic analysis. Use when working with economic time series that need to be decomposed into trend and cyclical components. Covers HP filter, log transformations for growth series, and correlation analysis of business cycles.

The English summary is being prepared. Showing the original description.

Parse SQLite databases into structured JSON data. Use when exploring unknown database schemas, understanding table relationships, and extracting map data as JSON.

The English summary is being prepared. Showing the original description.

Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.

The English summary is being prepared. Showing the original description.