Claude MarketplacesSubmit
awslabs avatar

Sdk Getting Started

awslabs/agent-pluginsOfficial

This handles the boring but essential preflight checks before any SageMaker or Bedrock work: SDK version, AWS region, execution role. It runs the validation directly without generating code, which is smart since you don't want to debug environment setup. The workflow references look comprehensive, covering both basic SDK setup and the trickier execution role resolution. Use it whenever someone says "getting started" or "set up", or just run it first in any SageMaker plan. The "don't ask for what you can look up" principle is good, it'll try to resolve your region and role before prompting you. Saves the back and forth.

GitHub stars
783
last updated
Jun 11, 2026
View on GitHub

Install

$ npx -y skills add awslabs/agent-plugins --skill sdk-getting-started --agent claude-code

Installs into .claude/skills of the current project.

Files

SDK Getting Started

Preflight checks to verify the user's environment can run SageMaker AI operations. The agent runs these checks directly (no code generation) and stores results in conversation context for downstream skills.

Principles

  1. Don't ask for what you can look up. Resolve region and role programmatically before asking the user.

Workflow

Read and follow references/sagemaker-python-sdk-setup.md.

References

  • references/sagemaker-python-sdk-setup.md - SageMaker Python SDK version, region, and execution role checks
  • references/execution-role-setup.md — Execution role resolution and validation
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/awslabs/agent-plugins
Categories
AI & Agent Building, Release Management, Productivity & Planning, Cloud & Infrastructure
License
Apache-2.0
First seen
Jun 11, 2026

More from awslabs/agent-plugins

All 32

Recommended

More AI & Agent Building
1callstackincubator avatardogfoodcallstackincubator/agent-skillsSystematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "e0skills.sh installs
2callstackincubator avatarreact-native-testingcallstackincubator/agent-skills>0skills.sh installs
3callstackincubator avatarvercel-react-native-skillscallstackincubator/agent-skillsA collection of agent-optimized React Native skills for AI coding assistants.0skills.sh installs
4cclank avatarkling-promptercclank/lanshu-awesome-ai-video-kit生成符合 Kling 3.0（可灵 3.0，快手）规则的视频提示词。三种写法自适应：4 部分基础公式（短视频）/ 5 层进阶公式（剧情+音频）/ 图生视频专用（只描述运动）。Kling 是 2026 年中文理解最强、原生音画同步、最长 2 分钟、支持角色定向发声、Motion Brush 的电影级模型。用于"用 Kli0skills.sh installs
5cclank avatarmodel-selectorcclank/lanshu-awesome-ai-video-kit根据用户的视频需求(场景、时长、音频、语言、平台限制、预算、是否需要本地部署/角色一致性等),从 16 个主流 AI 视频模型(12 商业 + 4 开源)中推荐最匹配的 1-3 个,并解释为什么。覆盖商业:Seedance 2.0、HappyHorse 1.0、Kling 3.0、Sora 2、Veo 3.1、**Ge0skills.sh installs
6cclank avatarseedance-promptercclank/lanshu-awesome-ai-video-kit把用户的自然语言视频需求转换为符合 Doubao Seedance 2.0 进阶公式的提示词（8 要素：精准主体+动作细节+场景环境+光影色调+镜头运镜+视觉风格+画质+约束条件）。用于"帮我写一个 Seedance 提示词"、"生成视频提示词"、"做个产品广告视频"、"用 Seedance 生成 XX"等触发场景。如0skills.sh installs