109 skills · sorted by relevance
Add or troubleshoot Table v9 features such as sorting, filtering, pagination, selection, merged cells, and column layout. Guidance helps check feature registration, dependencies, and row-processing settings, with references selected for the task.
Generates complete phenotype-scoring bioinformatics research designs for any disease context and any user-defined phenotype, pathway, process, signature, or molecular program. Use when a study centers on gene-set or feature-set definition, intersection with DEGs or candidate features, phenotype scoring, feature selection, diagnostic or stratification assessment, immune or cellular-resolution interpretation, network analysis, and optional orthogonal validation. Covers five study patterns (signature discovery, phenotype scoring, feature selection, immune/cellular interpretation, multi-layer validation) and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.
The English summary is being prepared. Showing the original description.
Build, inspect, and reuse Featuretools automated feature engineering workflows for EntitySets, DFS, feature matrices, primitive authoring, feature inspection, and selection.
The English summary is being prepared. Showing the original description.
Find Claude Academy learning resources that closely match questions about using Claude, its features, or team adoption. It supplements direct answers with a small selection of relevant courses, tutorials, worked examples, or product learning hubs.
Build web application features across the interface, API, and database, with authentication, input checks, and safe data handling. The skill guides technical design, implementation, error handling, and component testing in one workflow.
Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification, lambda.min, lambda.1se. NOT for: survival/Cox modeling, multiclass outcomes, single-cell data, or non-expression tables.
The English summary is being prepared. Showing the original description.
This is an advanced version of TDbasedUFE, which is a comprehensive package to perform Tensor decomposition based unsupervised feature extraction. In contrast to TDbasedUFE which can perform simple the feature selection and the multiomics analyses, this package can perform more complicated and advanced features, but they are not so popularly required. Only users who require more specific features can make use of its functionality.
The English summary is being prepared. Showing the original description.
Amazon reverse product selection: filter Amazon niches and keywords by 30+ business dimensions (market size & growth, price tiers & share, competition density & top concentration, demographics such as age/gender/income, review highlights & pain points) from a metrics pool aggregated from historical business insight reports. Trigger when users mention reverse product selection, metrics filtering, niche reverse lookup, blue ocean niche discovery, low-competition niche, newcomer-friendly niche, brand-fragmented market, pain-point entry, feature reverse lookup, pricing tier opportunity, demographic-based selection, or similar terms. Even if the user does not explicitly say "reverse product selection," trigger this skill whenever the request involves filtering Amazon niches that match specific business criteria.
The English summary is being prepared. Showing the original description.
Audit a focused part of an existing codebase, reconstruct its behavior and past decisions, and record gaps in reasoning, coding practices, features, and technology choices. Use the findings to plan, test, implement, and verify improvements.
Work on Handsontable core bugs, features, and TypeScript types using its architecture and implementation conventions. The skill directs tasks to specialist guides and outlines registration, compatibility, documentation, and testing checks for changes.
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization, normalization, interpolation, missing value handling, feature selection, or ANY data transformation task. Covers grouped time-series, cross-sectional, panel data. Detects: time travel leakage, causal inversion, ID misuse, semantic-numeric fallacies, distribution blindness. User's hard-won lessons from real project failures.
The English summary is being prepared. Showing the original description.
Detects and prevents data leakage in machine learning and mathematical modeling. Use after ML tasks involving data cleaning, feature engineering, data augmentation, algorithm development, normalization, missing value imputation, dimensionality reduction, feature selection, or time series modeling. Checks if features/statistics would be available at prediction time.
The English summary is being prepared. Showing the original description.
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes `vs project`; otherwise stop without taking action.
The English summary is being prepared. Showing the original description.
Interpret and explain a trained tabular machine-learning model (classification or regression) in MATLAB. Find which predictors, features, or columns matter most; explain why the model made a specific prediction, including diagnosing predictions it got wrong; show how a predictor affects the output; and compare how the model behaves across cohorts or subgroups. Uses model-agnostic techniques and model-native measures, and works on custom models (such as a dlnetwork) through a prediction function handle. Use for model interpretability, explainability, and feature-importance questions on tabular data, not for training, tuning, feature selection, deploying models, or models trained on image, text, signal, or other non-tabular data.
The English summary is being prepared. Showing the original description.
Designing side-by-side comparison tools (plan-compare, product-compare, alternative-compare) that help users decide rather than just listing features. Axis selection, default-comparison logic, recommendation discipline. Honest about feature-list-dump (every feature in a row, no decision support), hidden-recommendation (biased comparison pretending to be neutral), and honest-comparison-with-guidance (genuine comparison plus opinionated recommendation) patterns. Triggers on comparison tool, plan compare, product compare, alternative compare, vs page, decision support tool. Also triggers when conversion through comparison stages is poor, when users are abandoning at the comparison step, or when a comparison tool is being scoped for the first time.
The English summary is being prepared. Showing the original description.
Expert en data science (pandas, numpy, scikit-learn, feature engineering, model selection)
The English summary is being prepared. Showing the original description.
Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap, the conditional-vs-interventional Shapley choice, and the attribution-is-not-causation boundary. Use when interpreting an omics classifier, debugging shortcut/batch learning, or deciding whether an attribution ranking can be trusted as biology. For validated feature selection see machine-learning/biomarker-discovery; explanations are not a selection method.
The English summary is being prepared. Showing the original description.
Selects biomarker features from high-dimensional omics data using Boruta all-relevant selection, mRMR, LASSO/elastic-net, and stability selection, while controlling the leakage, irreproducibility, and correlated-feature traps that make most published signatures fail to replicate. Use when identifying candidate biomarkers, deciding between an all-relevant and a minimal-optimal selector, or judging whether a selected gene set is reproducible. For unbiased performance estimation of the resulting model see machine-learning/model-validation; for interpreting a trained model see machine-learning/prediction-explanation.
The English summary is being prepared. Showing the original description.
Write and register SGLang unit and end-to-end tests, from choosing models and file locations to reusing server fixtures. Follow project rules for meaningful assertions, CI registration, dependency mocking, and safe server cleanup after tests.
Review an AI plan through six questions covering evaluation examples, error targets, fallback behavior, regulatory risk, model choices, costs, and hiring. Produce a structured verdict with gaps to address and three concrete next steps.
Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).
The English summary is being prepared. Showing the original description.
Generates complete comorbidity-oriented shared-biomarker bioinformatics research designs from a user-provided disease pair and validation direction. Use when a study links two clinically related diseases through shared DEGs, enrichment, PPI hub genes, machine-learning feature selection, public diagnostic validation, gene-regulatory networks, immune infiltration, and optional downstream follow-up. Covers five study patterns (shared-DEG discovery, hub-gene prioritization, machine-learning biomarker selection, immune/regulatory interpretation, multi-layer validation) and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.
The English summary is being prepared. Showing the original description.
Generates complete process-related diagnostic biomarker bioinformatics research designs from a user-provided disease context, gene-family or pathway theme, and validation direction. Use when a study centers on process-related genes, DEG and WGCNA integration, machine-learning feature selection, nomogram-based diagnostic modeling, immune infiltration, regulatory-network analysis, and optional external or experimental validation. Covers five study patterns (process-DEG discovery, co-expression-module integration, machine-learning biomarker selection, diagnostic model/nomogram workflow, immune-regulatory interpretation and validation) and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.
The English summary is being prepared. Showing the original description.
How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.
The English summary is being prepared. Showing the original description.