dt-obs-aws

AWS cloud resource monitoring including EC2, RDS, Lambda, ECS/EKS, VPC networking, load balancers, S3, DynamoDB, SQS/SNS, and cost optimization. Use when analyzing AWS infrastructure, resource inventory, security compliance, capacity planning, or cost savings. Trigger: "show EC2 instances", "find RDS databases", "VPC resources", "AWS cost optimization", "Lambda functions", "ECS services", "security groups", "unattached EBS volumes", "AWS load balancer topology", "publicly accessible databases", "AWS dashboards". Do NOT use for explaining existing queries, product documentation questions, generic host CPU/memory metrics (use dt-obs-hosts), application-level tracing (use dt-obs-tracing), or log analysis (use dt-obs-logs).

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

86%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-engineered query-reference skill: executable DQL throughout, real one-level-deep references with clear load triggers, and no filler. The main improvement opportunities are consolidating the three overlapping navigation layers and adding explicit multi-step sequences with validation for complex analyses.

Suggestions

Consolidate the three navigation layers (inline '→' arrows, 'When to Load References', and the 'References' list) into a single load-conditions section to cut duplicated tokens — e.g., remove the per-workflow arrows or the trailing References list.

Remove the duplicated arrow pair at lines 220-221 where 'For serverless' and 'For containers' both point to serverless-containers.md.

Dimension	Reasoning	Score
Conciseness	The body is dense with Dynatrace-specific knowledge (smartscapeNodes, aws.object parsing, dt.traverse.history) and never explains concepts Claude already knows, but navigation is triplicated (inline arrows, the 'When to Load References' section, and the final References list) and lines 220-221 duplicate arrows pointing to the same file.	4 / 5
Actionability	Every workflow ships complete, copy-paste-ready DQL with realistic values (e.g., 'vpc-0be61db7c5d2d1bd1', 'tags[Environment] == "production"'), plus a pattern template table that generalizes the examples to common cases.	5 / 5
Workflow Clarity	Task-to-query routing is unambiguous and each workflow is a single read-only query with implicit null-handling checkpoints ('Check for null values after parsing', isNotNull guidance), but there are no explicit multi-step sequences or validation checkpoints, which anchor 5 requires.	4 / 5
Progressive Disclosure	The SKILL.md stays an overview covering the stated 80% of use cases, all 13 referenced files exist on disk, and references are one level deep with explicit per-file load conditions ('Load events.md when: Investigating what changed before or during a problem').	5 / 5
	Total	18 / 20 Passed

Description

95%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 strong description: it defines a clear AWS-monitoring niche, answers both what and when explicitly, provides natural trigger phrases, and disambiguates against sibling skills with explicit exclusions. The only weakness is that its capability verbs are generic while nouns carry the specificity.

Dimension	Reasoning	Score
Specificity	The description enumerates a broad set of AWS services and task categories ('resource inventory, security compliance, capacity planning, or cost savings'), giving concrete scope, though the action verbs themselves ('monitoring', 'analyzing') stay generic rather than naming specific operations as anchor 5 requires.	4 / 5
Completeness	It explicitly answers both what ('AWS cloud resource monitoring including EC2, RDS, Lambda, ECS/EKS...') and when ('Use when analyzing AWS infrastructure, resource inventory, security compliance, capacity planning, or cost savings'), supplemented by concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes an explicit Trigger list of natural user phrases — 'show EC2 instances', 'find RDS databases', 'unattached EBS volumes', 'publicly accessible databases', 'AWS load balancer topology' — with comprehensive coverage including service names and colloquial variants.	5 / 5
Distinctiveness Conflict Risk	The 'Do NOT use for...' clause redirects generic host metrics, tracing, and log analysis to named sibling skills (dt-obs-hosts, dt-obs-tracing, dt-obs-logs), carving out a clear AWS-specific niche with minimal conflict risk.	5 / 5
	Total	19 / 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: Dynatrace/dynatrace-for-ai
Path: skills/dt-obs-aws/SKILL.md
Commit: 47528b0

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.