CtrlK
BlogDocsLog inGet started
Tessl Logo

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 creating-ec2-image-builder-pipeline. Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A high-quality, token-efficient skill body that leads with critical gotchas, navigates to six real reference files, and gives concrete commands and troubleshooting fixes. The only notable gap is the absence of explicit validation checkpoints/feedback loops in the multi-step workflows, which is especially relevant for AMI rollouts and fleet operations.

Suggestions

Add explicit validate-then-proceed checkpoints to the AMI-rollout and autoscaling-fleet workflows (e.g., verify the new launch-template version passes a smoke test on one instance before kicking off instance refresh).

For instance refresh, document the rollback/validation loop: pin a numeric LT version, start refresh with a small instance-generation batch, confirm healthy before continuing, and how to roll back if the first batches fail.

Add a quick verification step to the SSM 'Connect to a private instance' workflow (e.g., confirm the instance appears as a managed node via describe-instance-information before opening a Session Manager session).

DimensionReasoningScore

Conciseness

Lean and action-dense throughout — every line carries operational signal (e.g., 'Set HttpPutResponseHopLimit=2 for bridge/awsvpc container workloads', 'Stop/start to migrate to new hardware (reboot won't)') with no padding or explanation of concepts Claude already knows like what EC2 or an AMI is.

3 / 3

Actionability

Concrete, executable guidance throughout — specific CLI flags ('--health-check-type ELB', 'complete-lifecycle-action CONTINUE'), exact values ('HttpPutResponseHopLimit=2', 'price-capacity-optimized'), named policies ('AmazonSSMManagedInstanceCore'), and a symptom/cause/fix troubleshooting table that is copy-paste ready.

3 / 3

Workflow Clarity

Workflows like 'Roll out a new AMI' and 'Stand up an autoscaling web fleet' list steps but omit explicit validation checkpoints and feedback loops; per the rubric, risky fleet/AMI operations without validate-then-proceed gating cap workflow clarity at 2.

2 / 3

Progressive Disclosure

Clear overview with two navigation tables and well-signaled one-level-deep references to six real bundle files (instance-selection.md, provisioning.md, auto-scaling.md, systems-manager.md, ami-management.md, troubleshooting.md), each linked contextually and verified to exist in ./references/.

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.

An exceptionally well-crafted description: concrete capabilities, abundant natural trigger terms, explicit when-to-use guidance, and rigorous scope boundaries that prevent conflicts with sibling skills. It avoids fluff and verbosity despite covering a large domain.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'instance-type selection', 'launch templates', 'Auto Scaling groups (scaling policies, instance refresh, mixed instances, Spot, warm pools, lifecycle hooks)', 'IMDSv2', 'placement groups', 'AMI lifecycle', 'Systems Manager fleet operations (Session Manager, Run Command, Patch Manager)' — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both: what it does ('Provisions, scales, and operates Amazon EC2 virtual-machine workloads') and when to use it ('Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity...'), satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

Strong natural phrasing users would actually say — 'InsufficientInstanceCapacity', 'CPU-credit/surplus charges', 'IMDSv2 401s', 'instances stuck in Pending:Wait', 'ASG not replacing unhealthy instances', 'SSH refused/timed out', 'instances missing as SSM managed nodes' — broad coverage of real-world problem terms.

3 / 3

Distinctiveness Conflict Risk

Clear EC2-fleet niche with explicit deconfliction — redirects single launches to launching-ec2-instance-with-best-practices, instance profiles to setting-up-ec2-instance-profiles, Image Builder to creating-ec2-image-builder-pipeline, and declares 'Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring', making mis-triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.