Cody skill library
Practical guidance for model APIs, MCP servers, managed agents, and retrieval-grounded systems.
5 skills
Open category page
microsoft/azure-skills
Microsoft's operational guide for building, evaluating, deploying, and managing Foundry agents and models. Best for teams already building managed agents and model workflows on Azure and Microsoft Foundry.
anthropics/skills
A design and implementation guide for MCP servers that expose external services to language models. Best for developers turning an existing API or internal service into a well-behaved MCP tool surface.
google/skills
Manages Google Agent Platform RAG corpora, files, retrieval, and grounded generation through the Gen AI SDK. Best for google Cloud teams operating a managed retrieval layer for grounded agent responses.
anthropics/skills
A current reference skill for Claude models, API patterns, tools, caching, streaming, MCP, and migration. Best for teams building directly on the Anthropic API or migrating a Claude integration across model generations.
google/skills
Google's implementation guide for Gemini through Vertex AI and Agent Platform. Best for projects using Gemini in Google Cloud rather than a provider-neutral model abstraction.
How the list was made
Cody's editors selected a focused set of agent skills that solve recognizable jobs, come from inspectable GitHub repositories, and show meaningful adoption or active maintenance.
Prefer focused skills that encode a repeatable workflow or a maintained domain playbook.
Favor clear ownership, active repositories, and meaningful adoption, then use community experience as a supporting signal.
Explain what each skill does, who it helps, and what to review before installing it.
Keep the collection small enough that users can install only what matches their work.
Browse the rebuilt prompt library for detailed, model-aware templates designed for GPT-5.6 and Claude Fable 5.1.
Explore prompt templates