Back to directory

AWS Agent Skills

A set of curated Agent Skills that give Claude Code and Codex reasoning-first expertise across 18 core AWS services, kept current with weekly documentation checks.

AWS Agent Skills

AWS Agent Skills equips Claude Code and Codex with curated, LLM-optimized knowledge across 18 core AWS domains, including IAM, Lambda, DynamoDB, S3, API Gateway, EC2, ECS, and EKS, covering real-world patterns, edge cases, and best practices for each service. Its skills are checked against AWS documentation on a weekly basis so they stay current with service changes.

The project argues that this reasoning-first approach complements rather than replaces an AWS MCP server: MCP is suited to live documentation lookups and API calls, while local, pre-compressed skills avoid streaming large docs or schemas into context, keeping the context window smaller, more predictable, and less exposed to extra credential surface.

It installs as a Claude Code or Codex plugin from a marketplace, from GitHub directly, or from a local path, and is released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.