aws-compute

Provisions, scales, and operates Amazon EC2 virtual-machine workloads: instance-type selection (Graviton/Arm64, burstable T credits, GPU, instance store vs EBS), launch templates, Auto Scaling groups (scaling policies, instance refresh, mixed instances, Spot, warm pools, lifecycle hooks), IMDSv2, placement groups, Elastic IPs, AMI lifecycle, and Systems Manager fleet operations (Session Manager, Run Command, Patch Manager). Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity, CPU-credit/surplus charges, IMDSv2 401s, instances stuck in Pending:Wait, ASG not replacing unhealthy instances, status-check failures, SSH refused/timed out, or instances missing as SSM managed nodes. For a single secure instance launch, the launching-ec2-instance-with-best-practices skill is more appropriate; for instance profiles, see setting-up-ec2-instance-profiles; for Image Builder, see amazon-ec2-image-builder. Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring.

Quality

90%

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

80%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.

The body is a well-structured index: concise, navigable, and free of padding, with concrete flag-level guidance and a strong symptom/cause/fix troubleshooting table. The main gap is that validation/feedback-loop detail for batch and rolling operations lives in references rather than inline, slightly capping workflow clarity.

Suggestions

Inline one explicit validation checkpoint per batch/rolling workflow (e.g., 'after instance refresh, confirm replacement instances pass ELB health before declaring complete') so the feedback loop is visible without opening a reference.

Move the parenthetical IMDSv1-fallback mechanics from the critical warning into provisioning.md to tighten the overview further.

Add at least one fully copy-pasteable command snippet in the SSM/connectivity workflow (e.g., the start-session or instance-profile attachment command) to lift actionability on the most common workflow.

Dimension	Reasoning	Score
Conciseness	Lean overview that assumes Claude's competence (no 'what is EC2' padding) and routes to reference files; a few explanatory clauses like the parenthetical IMDSv2 fallback detail add length that could be trimmed or moved to a reference.	4 / 5
Actionability	Gives concrete, runnable specifics (flag names like --health-check-type ELB, HttpPutResponseHopLimit=2, price-capacity-optimized Spot policy, complete-lifecycle-action CONTINUE) covering common cases; a couple of entries stay at the diagnostic level without a full command.	4 / 5
Workflow Clarity	Common Workflows sequence the end-to-end steps (template then ASG, new LT version then instance refresh) and the troubleshooting table pairs symptom with fix; validation feedback loops for the trickier batch ops are mostly deferred to references rather than stated inline.	4 / 5
Progressive Disclosure	Clean overview split across clearly signaled one-level-deep reference files (instance-selection, provisioning, auto-scaling, systems-manager, ami-management, troubleshooting), each linked from multiple navigation tables, all real files in ./references; no nested references.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is exemplary: concrete and comprehensive in what it covers, rich with natural trigger phrases and real error strings users encounter, and sharply bounded against adjacent skills. It fully answers both 'what' and 'when' with minimal padding.

Dimension	Reasoning	Score
Specificity	Lists many concrete, named capabilities (instance-type selection across Graviton/burstable/GPU/instance-store, launch templates, ASG scaling policies/instance refresh/Spot/warm pools/lifecycle hooks, IMDSv2, AMI lifecycle, SSM fleet operations) with comprehensive coverage and minimal abstraction.	5 / 5
Completeness	Explicitly states what it does (the provisioning/operations catalogue) and when to use it via the 'Applies to EC2 instance and fleet questions' clause with concrete triggers, plus explicit cross-skill routing for related needs.	5 / 5
Trigger Term Quality	Includes natural user-facing error/symptom phrases (InsufficientInstanceCapacity, CPU-credit/surplus charges, IMDSv2 401s, instances stuck in Pending:Wait, SSH refused/timed out, missing SSM managed nodes) plus named services and instance families users actually say.	5 / 5
Distinctiveness Conflict Risk	A clear EC2-focused niche with an explicit 'Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring' boundary and specific handoffs to sibling skills, minimizing conflict risk.	5 / 5
	Total	20 / 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: plugins/aws-core/skills/aws-compute/SKILL.md
Commit: 88a5fb3

Reviewed: 4 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.