Data & AI skills

Building robust document ingestion — chunking, metadata, and multi-format pipelines for search and RAG.

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

Build rich visualizations with Apache ECharts: option config, dataset transforms, large-data performance, and custom rendering. Use for complex dashboards and big datasets.

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

Elasticsearch search and analytics — mappings, queries, and cluster health — use when building search or log analytics.

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

Electronic health record analysis — phenotyping, missingness, bias, and observational study design with EHR data.

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

Generate and edit images with diffusion models: prompting, seeds, CFG, img2img, inpainting, conditioning, and API integration. Use when adding AI image generation to apps or workflows.

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

Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.

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

Analyze text data with NLP — preprocessing, embeddings, topic modeling, sentiment, classification, and evaluation. Use when turning unstructured text into structured insight.

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

Choosing colormaps scientifically — perceptual uniformity, color-vision deficiency, and matching map to data type.

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

Analyzing contact tracing data — network reconstruction, transmission chains, and evaluating tracing performance.

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

CSV processing done right — parsing edge cases, dialects, and large files — use when ingesting or exporting CSV data.

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

Run the data science workflow end to end — framing, exploration, feature engineering, modeling, validation, and communicating results. Use when turning raw data into decisions or predictions.

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

Manage ML datasets with the datasets ecosystem — loading, streaming, preprocessing, versioning, and sharing. Use when data handling (not modeling) is the bottleneck.

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

Build custom data visualizations with D3: selections, scales, axes, transitions, and reusable chart patterns. Use when off-the-shelf charts aren't enough.

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

Manage LLM context windows deliberately — budgeting, prioritization, summarization, and retrieval instead of dumping everything in. Use when prompts grow long, costs rise, or the model loses track of key details.

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

Crystal structure fundamentals — lattices, space groups, Miller indices, and reading crystallographic data correctly.

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

Design annotation pipelines that produce reliable training labels — guidelines, agreement measurement, and quality control.

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

NLP on clinical text — de-identification, concept extraction, phenotyping from notes, and LLM safety guardrails.

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

Estimate causal effects from observational and experimental data — DAGs, confounding control, quasi-experimental designs, and sensitivity analysis. Use when you need "what causes what," not just correlation.

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

Build dashboards with Chart.js: layout, KPI cards, cross-chart filtering, theming, and real-time panels. Use for operational and analytics dashboards.

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

ClickHouse columnar analytics — schema design, MergeTree tuning, and fast queries — use for OLAP and high-volume event data.

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

Working with observational climate data — reanalyses, station records, anomalies, trends, and honest uncertainty.

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

Translating coarse global climate projections to local scales — dynamical vs statistical downscaling, bias correction, and added value.

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

Split documents for retrieval effectively — fixed, semantic, structural, and hierarchical chunking with overlap tuning. Use when RAG retrieval quality depends on how documents are divided.

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

Build with Cohere's enterprise AI — Command models, Embed embeddings, and Rerank for retrieval pipelines.

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