Total 33,066 skills
Showing 12 of 33066 skills
Use when asked to parse, normalize, standardize, or convert dates from various formats to consistent ISO 8601 or custom formats.
Build UIs with shadcn/ui components. Covers CLI commands, component installation, theming with CSS variables, OKLCH colors, and customization patterns. Triggers on shadcn, shadcn-ui, add component, or theming questions.
Write AI-scannable technical documentation.
Convert between physical units (length, mass, temperature, time, etc.). Use for scientific calculations, data transformation, or unit standardization.
Generate structured, actionable build reports from Node.js build outputs (TypeScript, ESLint, Webpack, Vite). Groups errors by pattern, prioritizes issues, and suggests documented solutions. Use when analyzing build failures, debugging compilation errors, or reviewing warnings. Supports English and Spanish. | Genera reportes estructurados y accionables de builds Node.js (TypeScript, ESLint, Webpack, Vite). Agrupa errores por patrón, prioriza issues y sugiere soluciones documentadas. Usar para analizar fallos de build, debuggear errores de compilación o revisar warnings.
Compare document similarity using TF-IDF, cosine similarity, and Jaccard index. Use for plagiarism detection, duplicate finding, or content matching.
When the user wants to optimize free trial conversion -- including trial length, trial type selection, expiry flows, or trial email sequences. Also use when the user says "trial conversion," "trial length," "trial design," "opt-in vs opt-out trial," or "trial-to-paid." For activation, see activation-metrics. For feature gating, see feature-gating.
Detect language of text with confidence scores, support for 50+ languages, and batch text classification.
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a classification/regression task.
Generate styled word clouds from text with custom shapes, colors, fonts, and stopword filtering. Supports PNG/SVG export and frequency dictionaries.
Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization. Use when choosing vector stores, designing semantic search, or optimizing similarity search performance.
Testing patterns and best practices for unit, integration, and E2E testing.