Skills for Real Engineers. Straight from my .agents directory.
aws-lambda-microvms
Agent skill fromawslabs/agent-plugins
Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. Triggers on: Lambda MicroVMs, Firecracker isolation, snapshot-resumable compute, suspend/resume, sandboxed or untrusted code execution, AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, isolated security scanners, long-lived sessions, or port-listening servers (gRPC, WebSocket, custom TCP). For standard event-driven Lambda functions, use the aws-lambda skill instead.
How to install aws-lambda-microvms
npx skills add awslabs/agent-plugins# or add only this skill to Claude Code: copy the folder
plugins/aws-serverless/skills/aws-lambda-microvms/
# into
~/.claude/skills/aws-lambda-microvms/ (all projects)
.claude/skills/aws-lambda-microvms/ (one project)
1# AWS Lambda MicroVMs23> The AWS MCP server is recommended for sandboxed execution and audit logging.45AWS Lambda MicroVMs are serverless compute environments that combine Firecracker VM isolation with container-like efficiency. Each MicroVM:67- Runs your application as a **container inside a Firecracker microVM** — you can reproduce the environment locally.8- Runs Amazon Linux 2023 as the base OS inside the MicroVM.9- Boots from a **memory + disk snapshot** captured at image build time, so application init is skipped on run.10- Has a dedicated, TLS-terminated HTTPS endpoint reachable with an auth token.11- Can be **suspended and resumed** with state preserved; lives up to 8 hours.1213**Two-resource model:**1415- `MicrovmImage` — a versioned artifact built from `{S3 zip with Dockerfile} + baseImageArn`. Each version has per-architecture/chipset `Build`s.16- `Microvm` — a running instance created (`RunMicrovm`) from an image version.1718**Two roles:**1920- `buildRoleArn` — used during image build (S3 read, CloudWatch logs, optional ECR).21- `executionRoleArn` — assumed at runtime by the running MicroVM.2223## When to use2425### Choose Lambda MicroVMs when2627- **Analytics workloads** — isolated compute for data processing, ETL jobs, or query execution with strong tenant separation.28- **AI / agent code execution sandboxes** — fresh, isolated environment per session, fast resume between turns.29- **Interactive code playgrounds & notebooks** — Jupyter, REPLs, dev environments executing user code.30…
Excerpt shown under the repository's Apache-2.0 license.
More skills in agent-plugins
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
