aws-containers

Builds and deploys containerized workloads on Elastic Kubernetes Service (EKS), Elastic Container Service (ECS), Fargate, and ECR (Elastic Container Registry). Covers general EKS knowledge, Karpenter, AWS Load Balancer Controller and leveraging various open source Kubernetes projects with EKS. Covers general ECS knowledge, task definitions, Fargate services, ECS Exec, ECS Express Mode and ECS Managed Instances. Covers general Elastic Beanstalk knowledge, Elastic Beanstalk configuration and platforms supported by Elastic Beanstalk. Covers general ECR knowledge, ECR repository setup and lifecycle policies. Includes recommending, enabling, and reading Amazon ECS Action Logs to troubleshoot control-plane failures (deployment rollback/circuit-breaker, task placement, scaling, task replacement). Applies when deploying, debugging, or optimizing containers on AWS. Should be used instead of relying on internal knowledge for these services.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/core-skills/aws-containers/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

A well-structured routing skill with strong progressive disclosure and mostly actionable guidance. Its main weakness is conciseness: several service-description paragraphs restate AWS marketing language Claude already knows rather than adding procedural value.

Suggestions

Replace the vendor-style service overviews (EKS, ECS, ECR, Elastic Beanstalk paragraphs) with terse one-line role statements; assume Claude knows what these managed services are and keep only the skill-relevant distinctions and routing.

Add a concrete first-action example per major service (e.g. a one-line command or the key CLI subcommand) to lift actionability from mostly-executable to copy-paste ready.

For deploy/debug workflows, surface an explicit verify step (e.g. check rollout status or task health before declaring success) to add the validation checkpoint currently missing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with a clean routing table and guardrails, but several paragraphs restate marketing-style descriptions Claude already knows (e.g. 'EKS provides a fully managed Kubernetes service that eliminates the complexity of operating Kubernetes clusters...') and the ECS/Elastic Beanstalk sections read like vendor copy.	3 / 5
Actionability	Concrete and executable guidance dominates: the routing table maps user needs to specific reference files, the MCP-vs-local guardrail gives exact tool invocations ('file="references/ecs.md"'), and named tools (aws___read_documentation) plus the Action Logs proactive step are actionable. Minor gap: no inline commands or code examples for the most common first actions.	4 / 5
Workflow Clarity	Clear routing and a proactive Action Logs decision flow with an explicit conditional ('read action-logs.md before responding and follow its tiering'), plus a guardrail distinguishing load paths. It stops short of a 5 because there are no explicit validation/verify checkpoints for the deploy-or-debug operations the skill targets.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview with a well-signaled routing table pointing to one-level-deep hub references (eks.md, ecs.md, ecr.md, beanstalk.md), which themselves branch cleanly to second-level files; all referenced paths verified to exist, and navigation by user-need is explicit.	5 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 rich, third-person description that clearly states capabilities and explicit use-when triggers across the AWS container service family. Trigger terms are strong but somewhat jargon-heavy, and the multi-service breadth introduces minor overlap risk.

Suggestions

Consider trimming the long clause enumerating every sub-topic; a tighter service-level list with a pointer to coverage would preserve comprehensiveness while reducing verbosity.

Add a couple of plain-language trigger synonyms (e.g. 'Kubernetes on AWS', 'container deployment') alongside the service acronyms to widen natural-term matching.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions across many AWS container services — 'Builds and deploys containerized workloads', 'recommending, enabling, and reading Amazon ECS Action Logs to troubleshoot control-plane failures', covering EKS, ECS, Fargate, ECR, and Elastic Beanstalk topics.	5 / 5
Completeness	Explicitly answers both what (the enumerated build/deploy/troubleshoot capabilities) and when — 'Applies when deploying, debugging, or optimizing containers on AWS. Should be used instead of relying on internal knowledge for these services.'	5 / 5
Trigger Term Quality	Strong, natural service and feature terms ('EKS', 'ECS', 'Fargate', 'ECS Exec', 'task definitions', 'lifecycle policies') that users would say, though it leans on service jargon and offers few plain-synonym variations beyond the named products.	4 / 5
Distinctiveness Conflict Risk	The AWS-containers niche is distinctive and unlikely to fire for unrelated skills, but the very broad scope across five services creates some overlap risk with a hypothetical separate per-service skill.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aws/agent-toolkit-for-aws
Path: skills/core-skills/aws-containers/SKILL.md
Commit: 57ce9ed

Reviewed: 6 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.