CtrlK
BlogDocsLog inGet started
Tessl Logo

eks-troubleshooting

EKS troubleshooting and debugging guide covering pod failures, cluster issues, networking problems, and performance diagnostics. Use when diagnosing cluster issues, debugging pod failures (CrashLoopBackOff, Pending, OOMKilled), resolving networking problems, investigating performance issues, troubleshooting IAM/IRSA permissions, fixing image pull errors, or analyzing EKS cluster health.

68

Quality

84%

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

68%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 highly actionable, command-rich troubleshooting guide with a clear triage workflow and well-organized one-level references. Its main weaknesses are redundancy between the workflow and command catalog, and missing validation checkpoints before the destructive emergency operations.

Suggestions

Add an explicit verification checkpoint before destructive emergency operations (e.g., 'Confirm pod is truly stuck with kubectl get pod before --force delete') and a re-check step afterward.

Dedupe the kubectl commands that appear in both the diagnostic workflow and the 'Essential kubectl Commands' section — keep the workflow lean and point to the catalog for the full reference.

Move the inline prevention/probe YAML into a reference file so SKILL.md stays a focused diagnostic overview.

DimensionReasoningScore

Conciseness

Largely efficient and free of concept-explanation padding, but the 'Essential kubectl Commands' catalog repeats commands (describe pod, get nodes, get events) already shown in the diagnostic workflow, and some inline prevention YAML could live in a reference file.

3 / 5

Actionability

Densely populated with copy-paste-ready kubectl and aws CLI commands with real flags, JSONPath examples, concrete exit codes (137/139/143), and complete YAML resource specs covering the common EKS failure cases.

5 / 5

Workflow Clarity

The triage workflow is clearly sequenced (Initial Triage → Identify Problem Area → Deep Dive), but the Emergency Procedures section runs destructive force-delete/drain operations ('kubectl delete pod --force', 'kubectl patch pod finalizers:null', 'kubectl drain --force') without a verify-before-act validation checkpoint, capping the score per the destructive-operations rule.

3 / 5

Progressive Disclosure

SKILL.md serves as an overview with one-level-deep, clearly signaled markdown links to real reference files (cluster-issues.md, workload-issues.md, networking-issues.md); good structure, though some inline command-catalog and prevention content could be split out.

4 / 5

Total

15

/

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 specific, trigger-rich, and answers both what and when explicitly in third person. It is a strong, low-conflict description with comprehensive concrete actions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — 'covering pod failures, cluster issues, networking problems, and performance diagnostics' plus 'diagnosing... debugging pod failures... resolving networking problems... troubleshooting IAM/IRSA permissions, fixing image pull errors, analyzing EKS cluster health' — comprehensive coverage of specific troubleshooting actions.

5 / 5

Completeness

Explicitly answers both 'what' ('EKS troubleshooting and debugging guide covering...') and 'when' ('Use when diagnosing cluster issues, debugging pod failures...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes the natural terms an operator would actually say — 'EKS troubleshooting', 'CrashLoopBackOff', 'Pending', 'OOMKilled', 'IAM/IRSA', 'image pull errors', 'networking problems' — covering synonyms and specific error states.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to EKS troubleshooting with distinct, specific triggers (CrashLoopBackOff, IRSA, image pull errors) that are unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

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

skill_md_line_count

SKILL.md is long (626 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.