Skills

Открытый реестр Skills для ИИ-агентов — структурированные промпты и рабочие процессы с рекомендуемыми моделями, примерами и совместимыми инструментами.

Некоторые описания переведены автоматически в рамках пилота и пока не проверены редактором.

Добавить Skill

Skills

45

Категории

9

Совместимые инструменты

6

Участники

1

Показано 22–42 из 45

Multi-Agent OrchestratorПродвинутый

Designs multi-agent systems where a coordinator delegates sub-tasks to specialist agents, verifies intermediate results, and synthesizes a final answer. Covers agent role definition, routing and delegation strategy, shared memory and message passing, verification loops, cost and latency budgeting, and failure handling across frameworks like LangGraph, CrewAI, or a custom orchestrator.

3 модели
Dependency UpgraderСредний

Plans and executes safe dependency upgrades across a project. Analyzes current versions, reads changelogs and release notes for breaking changes, sequences upgrades to minimize risk, applies required code migrations, and verifies with builds and tests. Works across npm, pip, Maven, Cargo, and Go modules.

3 модели
Database Migration WriterСредний

Writes safe, reversible database schema migrations and the corresponding rollback scripts. Plans zero-downtime changes using expand-and-contract patterns, handles data backfills and index creation without locking, and generates migrations for tools like Alembic, Flyway, Prisma, Knex, and Rails ActiveRecord with clear up/down steps.

3 модели
Code Comment GeneratorНачальный

Adds clear, accurate inline comments and API doc blocks to existing code without changing behavior. Generates docstrings and structured comments (JSDoc, Google/NumPy style, Javadoc, Rustdoc) that explain intent, parameters, return values, side effects, and edge cases, while avoiding noisy comments that merely restate the code.

4 модели
GraphQL Schema GeneratorСредний

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.

4 модели
Mobile App PrototypingСредний

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.

3 модели
GitHub WorkflowСредний

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.

4 модели
API Client GeneratorСредний

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.

4 модели
AI Agent BuilderПродвинутый

Designs and scaffolds AI agent architectures including tool definitions, system prompts, memory strategies, and orchestration logic. Supports multi-agent workflows, ReAct patterns, function calling schemas, and MCP server configurations. Helps structure agents that are reliable, observable, and easy to debug.

4 модели
System DesignПродвинутый

Helps architect scalable distributed systems by analyzing requirements and producing high-level architecture diagrams, component breakdowns, data flow descriptions, and technology recommendations. Covers load balancing, caching strategies, database selection, message queues, and failure handling patterns.

4 модели
Git Conflict ResolverСредний

Analyzes and resolves git merge conflicts by understanding the intent of both sides. Examines the conflict markers, surrounding context, and commit history to produce a correct merged result that preserves both changes without breaking functionality.

4 модели
API Error HandlerСредний

Designs and implements comprehensive error handling for APIs. Covers error response formats (RFC 7807 Problem Details), HTTP status code selection, error logging strategies, retry logic, and client-friendly error messages with proper i18n support.

3 модели
TypeScript Type GeneratorСредний

Generates TypeScript type definitions from various sources — JSON data, API responses, database schemas, or plain descriptions. Produces strict types with proper generics, utility types, discriminated unions, and JSDoc comments.

4 модели
Code ExplainerНачальный

Explains complex code in plain language at the requested level of detail. Breaks down algorithms, design patterns, and architecture decisions. Adapts explanation depth from high-level overview to line-by-line walkthrough based on audience.

4 модели
React Component GeneratorСредний

Generates production-ready React components with TypeScript, proper props interfaces, accessibility attributes, responsive design, and test files. Follows modern patterns including Server Components, Suspense boundaries, and composition over inheritance.

4 модели
OpenAPI Spec GeneratorСредний

Generates complete OpenAPI 3.1 specifications from API descriptions, existing code, or route definitions. Includes request/response schemas, authentication, error responses, examples, and server configurations. Produces valid YAML ready for Swagger UI.

3 модели
Prompt EngineeringПродвинутый

Designs, optimizes, and iterates on prompts for LLM applications. Covers system prompt design, few-shot examples, chain-of-thought reasoning, output formatting, and prompt testing strategies. Helps build reliable AI-powered features.

3 модели
Debugging AssistantСредний

Systematic debugging workflow that helps identify, isolate, and fix bugs. Follows a structured approach: reproduce, localize, reduce, fix, guard. Analyzes error messages, stack traces, and logs to pinpoint root causes rather than symptoms.

4 модели
API DesignПродвинутый

Проектирует RESTful- и GraphQL API по принципу «сначала контракт». Охватывает структуру эндпоинтов, схемы запросов и ответов, обработку ошибок, версионирование, пагинацию, аутентификацию и ограничение частоты запросов. Создаёт спецификации OpenAPI/Swagger и заготовки реализации.

3 модели
Code TranslationПродвинутый

Translates code between programming languages while preserving logic, idioms, and best practices of the target language. Handles differences in type systems, error handling, concurrency models, and standard library APIs. Produces idiomatic target code, not line-by-line transliteration.

3 модели
Code ReviewСредний

Автоматизированная проверка кода с практическими рекомендациями по качеству, возможным ошибкам, производительности, уязвимостям безопасности и нарушениям стиля. Анализирует изменения с тщательностью старшего инженера и предлагает конкретные исправления с примерами кода.

4 модели

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.

Добавить на GitHub