dt-obs-kubernetes
Kubernetes clusters, pods, nodes, workloads, storage, networking, and resource relationships. Query K8s inventory, diagnose degraded deployments and pod failures, investigate rollouts, audit ingress and network policies.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/dt-obs-kubernetes/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent specificity and domain-specific trigger terms that clearly carve out a Kubernetes niche. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. Adding that clause would elevate this from a good description to an excellent one.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Kubernetes, K8s, container orchestration, pod issues, deployment problems, or cluster management.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query K8s inventory, diagnose degraded deployments and pod failures, investigate rollouts, audit ingress and network policies.' Also enumerates specific resource types: clusters, pods, nodes, workloads, storage, networking. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with both resource types and actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the listed capabilities, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Kubernetes', 'K8s', 'clusters', 'pods', 'nodes', 'deployments', 'pod failures', 'rollouts', 'ingress', 'network policies', 'workloads', 'storage', 'networking'. These are all terms a user would naturally use when seeking Kubernetes help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with Kubernetes-specific terminology (K8s, pods, nodes, ingress, network policies, rollouts). Very unlikely to conflict with other skills due to the clear Kubernetes niche and domain-specific trigger terms. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable DQL queries for Kubernetes monitoring via Dynatrace. Its main strengths are the executable code examples, clear entity type taxonomy, and excellent progressive disclosure to reference files. The primary weaknesses are some unnecessary best-practice content that Claude already knows and a lack of diagnostic decision trees or validation checkpoints in the workflows.
Suggestions
Remove or significantly trim the 'Monitoring Recommendations' and 'Configuration Standards' sections, as these are general K8s best practices Claude already knows and don't add Dynatrace-specific value.
Add diagnostic decision trees to troubleshooting workflows (e.g., 'If phase is Pending → check node capacity → check scheduling constraints → check resource requests') to improve workflow clarity with explicit branching logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary content like the 'Monitoring Recommendations' and 'Configuration Standards' sections which are general Kubernetes best practices Claude already knows. The 'When to Use This Skill' section largely duplicates the description and could be trimmed. | 2 / 3 |
Actionability | Excellent actionability with fully executable DQL queries covering cluster health, resource optimization, pod troubleshooting, security assessment, and scheduling analysis. Every workflow includes copy-paste ready queries with clear field selections and filters. | 3 / 3 |
Workflow Clarity | Workflows are presented as numbered sections with clear queries, but they lack explicit validation checkpoints and feedback loops. For example, the troubleshooting workflow doesn't guide through a diagnostic sequence (check phase → check events → check logs → check resources), and there's no 'if X then do Y' decision logic for error recovery. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference table linking to 8 specialized files covering cluster inventory, labels, pod debugging, workload health, storage, ingress, and network policies. The main skill provides a solid overview with common workflows while deferring deep-dive content to well-organized reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dynatrace/dynatrace-for-ai
- Commit
4991356
- 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.