Skills
Открытый реестр Skills для ИИ-агентов — структурированные промпты и рабочие процессы с рекомендуемыми моделями, примерами и совместимыми инструментами.
Skills
100
Категории
9
Совместимые инструменты
7
Участники
2
Показано 64–84 из 100
Parses and analyzes application, system, and access logs to surface errors, anomalies, and root causes. Correlates events across services, identifies recurring patterns and spikes, extracts structured fields from unstructured lines, and produces a prioritized summary with likely causes and recommended next steps.
Designs GraphQL schemas from domain descriptions or existing data models. Produces typed SDL with queries, mutations, subscriptions, input types, enums, and interfaces, following naming conventions, pagination patterns (Relay-style connections), and error-handling best practices. Can also generate resolvers scaffolding and map schemas to existing REST or SQL backends.
Extracts structured data from PDFs and scanned documents — invoices, receipts, forms, contracts, reports, and tables. Returns clean, typed output (JSON, CSV, or Markdown tables), handles multi-page layouts and nested tables, and flags low-confidence fields for review. Uses vision-capable models for image-based and scanned PDFs.
Generates and assists with incident response procedures for production systems. Helps with root cause analysis, creates runbooks for common failure modes, builds communication templates for stakeholders, and produces post-incident review documents. Supports SRE and on-call workflows.
Generates comprehensive load testing scripts and configurations for APIs. Supports k6, Locust, Artillery, and JMeter formats. Creates realistic traffic patterns, ramp-up scenarios, and threshold definitions. Includes analysis templates for identifying bottlenecks and capacity planning.
Transcribes audio recordings into structured text with speaker diarization, timestamps, and formatting. Supports meeting recordings, interviews, podcasts, and lectures. Handles multiple languages and accents with automatic language detection and optional translation.
Generates mobile application prototypes and implementations for iOS and Android. Creates SwiftUI views, Jetpack Compose layouts, and React Native components from descriptions or wireframe images. Handles navigation patterns, state management, and platform-specific design guidelines.
Crafts App Store metadata — title, subtitle, keyword field, and description — that maximizes both search visibility and conversion rate. Applies platform-specific character limits and indexing rules for iOS and Android, provides multiple copy variants per field, and outputs a keyword coverage matrix with before/after comparison.
Discovers, evaluates, and prioritizes App Store keywords for mobile apps. Expands seed keywords using autocomplete suggestions, competitor rankings, and category analysis, then scores each keyword by volume, difficulty, and relevance to build a prioritized keyword strategy with primary, secondary, long-tail, and aspirational buckets.
Builds and evaluates time series forecasting models using statistical and ML approaches. Supports ARIMA, Prophet, LSTM, Transformer-based models, and foundation models like TimesFM. Handles seasonality detection, trend decomposition, anomaly detection, multi-step forecasting, and backtesting with proper train/test splits for financial, IoT, and scientific time series data.
Performs geospatial data analysis, mapping, and spatial statistics using GeoPandas, Shapely, Rasterio, and Folium. Supports vector and raster operations, coordinate transformations, spatial joins, buffer analysis, satellite imagery processing, choropleth mapping, and route optimization for GIS and remote sensing workflows.
Analyzes complex networks and graphs using NetworkX, igraph, and PyTorch Geometric. Supports social network analysis, biological interaction networks, knowledge graphs, and citation networks. Performs community detection, centrality analysis, link prediction, graph neural networks, and network visualization with force-directed layouts.
Sets up and manages machine learning experiment tracking, hyperparameter optimization, and model registry workflows. Integrates with MLflow, Weights & Biases, and Optuna for systematic experimentation. Handles metric logging, artifact storage, model versioning, reproducibility, and automated hyperparameter search with early stopping.
Creates publication-quality scientific figures and plots using matplotlib, seaborn, and plotly. Supports common scientific plot types including heatmaps, volcano plots, survival curves, network graphs, phylogenetic trees, and multi-panel figures with proper statistical annotations, color-blind safe palettes, and journal formatting.
Designs and implements A/B testing experiments including hypothesis formulation, sample size calculation, variant configuration, metric definition, and statistical analysis planning. Covers both frontend feature flags and backend experiment frameworks.
Interacts with GitHub via the gh CLI for managing issues, pull requests, CI runs, releases, and repository settings. Automates common GitHub workflows including PR creation with proper descriptions, issue triage, release drafting, and CI debugging.
Generates professional PowerPoint presentations from text descriptions, outlines, or research notes. Creates structured slide decks with appropriate layouts, bullet points, speaker notes, and visual hierarchy. Outputs valid PPTX files or structured JSON for presentation frameworks.
Creates production-grade frontend interfaces with high design quality. Generates complete UI components, pages, and layouts using modern frameworks (React, Vue, Svelte) with Tailwind CSS or CSS-in-JS. Focuses on unique, polished designs that avoid generic AI aesthetics — emphasizing typography, spacing, color harmony, and micro-interactions.
Generates type-safe API client SDKs from OpenAPI specs, API documentation, or example requests. Produces clean, well-typed client code with error handling, retry logic, pagination helpers, and authentication setup. Supports TypeScript, Python, Go, and Rust.
Transforms complex technical concepts into clear, well-structured documentation for different audiences. Produces README files, architecture decision records (ADRs), runbooks, onboarding guides, and technical blog posts. Follows documentation best practices with consistent tone, proper formatting, and useful examples.
Generates complete, responsive landing pages from a product description or brief. Produces semantic HTML, modern CSS (Tailwind or vanilla), and optional JavaScript for interactions. Follows conversion-optimized layouts with hero sections, features, social proof, pricing, and CTAs.
Skills и MCP-серверы
в чём разница?Skillsописывают, что делать
Skill объединяет инструкции, пример промпта и рекомендуемые модели, чтобы агент стабильно выполнял задачу. Skills добавляют знания, а не новые подключения.
MCP-серверыописывают, как подключиться
MCP-сервер расширяет возможности агента, подключая его к реальным системам: базам данных, API и файлам. MCP добавляет подключения и действия, а не инструкции к задаче.
Простое правило: выбирайте Skill, когда модели нужно хорошо выполнить задачу, и MCP-сервер, когда ей нужен доступ к инструменту или системе. Их можно сочетать: Skill может использовать инструменты MCP-сервера.
Создали полезный Skill?
Добавьте SKILL.md в открытый реестр, который поддерживает сообщество.