Skills

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

Добавить Skill

Skills

35

Категории

9

Совместимые инструменты

5

Участники

1

Показано 22–35 из 35

Sentiment AnalysisНачальный

Classifies the sentiment and emotional tone of text — reviews, support tickets, social posts, and survey responses. Supports document-level and aspect-based sentiment, returns confidence scores and representative quotes, and aggregates trends across large batches with themes and actionable insights.

4 модели
Weather LookupНачальный

Fetches current weather conditions and forecasts for any location using free public APIs. Provides temperature, humidity, wind, precipitation probability, and multi-day forecasts. Useful for agents that need environmental context for travel planning, event scheduling, or outdoor activity recommendations.

4 модели
Web Content SummarizerНачальный

Summarizes web pages, PDFs, articles, and documents into concise, structured summaries. Extracts key points, main arguments, data, and conclusions. Supports multiple output formats including bullet points, executive summaries, and structured notes with citations.

4 модели
Brainstorm FacilitatorНачальный

Facilitates structured brainstorming sessions using proven ideation frameworks — SCAMPER, Six Thinking Hats, How Might We, Crazy Eights, and more. Generates diverse ideas, challenges assumptions, and helps converge on the strongest concepts.

3 модели
Environment Config GeneratorНачальный

Generates .env files, configuration schemas, and environment variable documentation from application requirements. Includes validation rules, default values, required vs optional flags, and example values. Supports multiple environments (dev/staging/prod).

3 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
Test Data GeneratorНачальный

Generates realistic test data, fixtures, and seed files for databases and APIs. Creates data that respects constraints (foreign keys, unique fields, valid formats) and covers edge cases. Supports JSON, SQL, CSV, and factory patterns.

4 модели
Professional Email WriterНачальный

Drafts professional emails for various business contexts — follow-ups, introductions, requests, escalations, and announcements. Adapts tone from formal to friendly based on audience and relationship. Keeps messages concise and action-oriented.

3 модели
Changelog GeneratorНачальный

Generates structured changelogs from git history, commit messages, or PR descriptions. Follows Keep a Changelog format, groups changes by type (Added, Changed, Fixed, Removed), and highlights breaking changes. Supports semantic versioning recommendations.

3 модели
Cron Expression BuilderНачальный

Builds and explains cron expressions from natural language schedules. Supports standard cron (5-field), extended cron (6-field with seconds), and cloud-specific formats (AWS EventBridge, Google Cloud Scheduler). Validates expressions and shows next run times.

3 модели
PR Description GeneratorНачальный

Generates clear, structured pull request descriptions from code diffs. Includes summary of changes, motivation, testing notes, and reviewer guidance. Follows team conventions and links related issues automatically.

3 модели
Error Message ImproverНачальный

Rewrites vague or technical error messages into clear, actionable user-facing messages. Considers the audience (end-user vs developer), suggests error codes, and provides guidance on what the user can do to resolve the issue.

3 модели
Commit Message WriterНачальный

Generates clear, conventional commit messages from code diffs. Follows Conventional Commits specification with appropriate type prefixes, scopes, and descriptions. Handles breaking changes, multi-file changes, and produces both concise subjects and detailed bodies.

4 модели
Regex BuilderНачальный

Builds, explains, and tests regular expressions from natural language descriptions. Supports multiple regex flavors (PCRE, JavaScript, Python, Go). Provides step-by-step breakdowns, test cases, and performance considerations for complex patterns.

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