Подборка installable AI Agent Skills для developer workflow в openai powered для Claude Code, Cursor и Windsurf.
Эта подборка сфокусирована на инструментах, которые используют модели OpenAI в практических процессах разработки. Сюда входят решения для проектирования промптов, сборки агентов, помощи в коде, оценки качества и наблюдаемости в рантайме. Цель — не перечисление протоколов, а выбор инструментов, улучшающих ежедневные инженерные результаты: быстрее итерации, надежнее контроль качества и лучше операционная прозрачность. Некоторые решения также поддерживают MCP, но центральная тема — OpenAI-ориентированные workflow и продуктивность разработчиков.
A collection page should not just add more cards to the screen. It should explain why these skills belong together, how the next step moves into installation and validation, and which path should continue the decision afterwards.
This collection should not trap users in comparison mode or pretend to install the whole collection. Its job is to narrow the shortlist to one skill, then send the next click into installation, validation, and rollout. Installation happens on the skill path.
Start with the install guide so the first OpenAI tool trial has a concrete setup path.
Open the Install PathOnce the install path is clear, move into the solution, CLI, or editorial surface that best matches this collection. That keeps platform, framework, and operations demand narrowing into a more verifiable high-intent journey.
A scenario page for users who already know the workflow problem they need to solve.
High-intent solution pages are safer recovery surfaces than broad skill detail expansion.
An editorial guide that explains why certain skills are trusted and how to choose among them.
Editorial guides let the site lead with reasoning instead of raw inventory.
Reviewed on 2026-04-17 for setup clarity, eval usefulness, runtime visibility, and maintainer reliability. We kept the tools that help OpenAI teams move from experiments to repeatable production routines.
OpenAI visitors usually arrive with a concrete job: improve prompts, add evals, debug runtime behavior, or make agent operations easier to hand off. This page narrows the shortlist around those jobs.
Use this page when you need one OpenAI stack that connects prompt work, evals, and runtime checks without creating a messy tool chain.
Treat this collection as a filter when quality and observability need to catch up with OpenAI usage.
Guide for implementing oRPC contract-first API patterns in Dify frontend. Trigger when creating or updating contracts in web/contract, wiring router composition, integrating TanStack Query with typed contracts, migrating legacy service calls to oRPC, or deciding whether to call queryOptions directly vs extracting a helper or use-* hook in web/service.
db-migrations - это навык для управления базой данных
Generate and verify E2E tests for a feature. Explores live app, creates test plan, generates tests, runs and fixes until passing.
Session start - check progress, suggest next task
TypeScript SDK patterns for Opik. Use when working in sdks/typescript.
Generate customizable widget plugins for the prompts.chat feed system
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: AI SDK, Vercel AI SDK, generateText, streamText, add AI to my app, build an agent, tool calling, structured output, useChat.
Do not reset back to the generic directory. Move sideways through these adjacent high-intent collections to narrow the shortlist toward the install path that best matches your team.
A high-trust collection that lets the site lead with official and strongly verified ecosystems instead of random long-tail repos.
Trusted-brand collections are the fastest way to rebuild authority after pruning.
A workflow-first collection that explains why related skills belong together and what job they solve.
Workflow collections add first-party judgment that generic skill detail pages struggle to communicate.
A platform-specific collection for one of the clearest demand clusters in the product ecosystem.
Platform collections let the site recover with narrower, more trustworthy topical intent.
A clean surface for editor-specific demand with explicit workflow intent.
Editor-specific demand should land on curated surfaces, not random repo coverage.
This collection should not keep users browsing forever. These three questions explain how to shortlist, install, and validate the next step.
Эти подборки построены вокруг автоматизации рабочих процессов, документов, данных и переиспользуемых стеков навыков.
Каталог лучше подходит для прямого поиска, а подборки помогают найти взаимодополняющие навыки, объединённые вокруг рабочего процесса.
Да. Навыки в этих подборках обычно работают в Claude Code, Cursor, Windsurf и других поддерживаемых средах через единый процесс установки.
These are the supporting surfaces for this collection after the install direction is clear and the primary next paths have already narrowed the decision.
A use-case page for users searching for repeatable automation patterns instead of one-off tools.
Workflow automation demand is easier to satisfy with curated intent clusters than with flat directory coverage.
A workflow-first collection that explains why related skills belong together and what job they solve.
Workflow collections add first-party judgment that generic skill detail pages struggle to communicate.