aws-lambda-microvms

Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, actionable body with executable commands, a sequenced workflow with validation hooks, and clean one-level progressive disclosure. The main weakness is mild redundancy in the 'When to use' section that repeats the frontmatter's use-case enumeration.

Suggestions

Collapse the 'Choose Lambda MicroVMs when' bullet list and the prose recap at line 41 into a single canonical list; both duplicate trigger use cases already in the frontmatter description.

Remove the line 41 prose summary ('In general, Lambda MicroVMs are suited for...') since it restates the bullets immediately above it without adding new information.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (tables, commands, limits, no 'what is a container' filler), but the use-case list in 'Choose Lambda MicroVMs when' and the prose recap at line 41 duplicate triggers already in the frontmatter and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready CLI commands (create-microvm-image, run-microvm, create-microvm-auth-token, websocat) with real flags plus concrete hook timeout and size-limit tables.	3 / 3
Workflow Clarity	A clearly sequenced 0–6 'Typical workflow' with a pre-flight regional-availability check and validation feedback via the /ready and /validate hooks (503-until-ready retry semantics), matching the explicit-checkpoints anchor.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with a well-signaled, one-level-deep 'Reference index' to six real reference files (all verified present), each with a one-line scope description for easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, third-person description with explicit 'what' and 'when' guidance and a distinct niche. Its only weakness is verbosity — the use-case enumeration is exhaustive — but against the rubric anchors it meets level 3 on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Builds, runs, debugs, and operates applications' — tied to a specific compute platform, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (builds/runs/debugs/operates on Lambda MicroVMs) and 'when' via three explicit trigger clauses ('Applicable when', 'Also suited for', 'Also applicable when').	3 / 3
Trigger Term Quality	Covers many natural terms a user would say — 'AI/agent code-execution sandboxes', 'interactive code playgrounds and notebooks (Jupyter, REPLs)', 'reinforcement-learning environments', 'sessionful game or simulation servers' — with broad variation rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Firecracker-isolated, snapshot-resumable serverless MicroVMs) with distinct triggers unlikely to fire for ordinary Lambda functions or EC2.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/serverless-skills/aws-lambda-microvms/SKILL.md
Commit: 222ce56

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.