k8s-manifest-generator
Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when generating Kubernetes YAML manifests, creating K8s resources, or implementing production-grade Kubernetes configurations.
86
81%
Does it follow best practices?
Impact
97%
1.15xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
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.
This is a strong skill description that clearly communicates what it does (creates specific Kubernetes resource types with production standards) and when to use it (with an explicit 'Use when' clause containing natural trigger terms including the K8s abbreviation). It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and resource types: 'Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets' with qualifiers like 'production-ready', 'best practices and security standards'. | 3 / 3 |
Completeness | Clearly answers both 'what' (create production-ready Kubernetes manifests for specific resource types following best practices) and 'when' (explicit 'Use when' clause covering generating YAML manifests, creating K8s resources, or implementing production-grade configurations). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Kubernetes manifests', 'K8s resources', 'Kubernetes YAML', 'Kubernetes configurations', 'Deployments', 'Services', 'ConfigMaps', 'Secrets', and the abbreviation 'K8s'. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Kubernetes manifest generation with specific resource types named. The domain is distinct enough (Kubernetes/K8s) that it's unlikely to conflict with general YAML, Docker, or other infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, production-ready Kubernetes manifest templates with good workflow sequencing and validation steps. However, it is severely bloated—much of the content explains concepts Claude already knows (what ConfigMaps are, basic kubectl troubleshooting, storage access modes) and repeats guidance across sections. The progressive disclosure strategy references external files that don't exist in the bundle, and the main file contains far too much inline content that should be delegated to those references.
Suggestions
Cut the file by at least 50%: remove 'Purpose', 'When to Use', 'Questions to ask', 'Next Steps', 'Related Skills', 'Troubleshooting', and the 'Best Practices Summary' (which repeats inline guidance). Claude knows what Kubernetes resources are and how to use kubectl.
Move 'Common Patterns', security context details, and multi-resource organization guidance into the referenced files (e.g., references/deployment-spec.md, assets/) and actually provide those bundle files.
Consolidate inline best practices into brief bullet annotations next to each YAML template rather than repeating them in separate sections.
Remove explanatory text like 'For sensitive data:', 'For application configuration:', 'Choose the appropriate Service type:' — the YAML kind field and context make these obvious.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Includes extensive 'Questions to ask' lists, 'When to Use This Skill' bullets, explanations of concepts Claude already knows (what ConfigMaps are for, what StatefulSets are, storage access modes), a 'Purpose' section restating the title, 'Next Steps' and 'Related Skills' sections, and a 'Troubleshooting' section with basic kubectl commands Claude already knows. The best practices summary largely repeats guidance already given inline. | 1 / 3 |
Actionability | Provides fully executable, copy-paste-ready YAML manifests for every resource type (Deployment, Service, ConfigMap, Secret, PVC, SecurityContext). Validation commands are concrete and executable. Templates are well-structured with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | Clear 10-step sequential workflow from requirements gathering through validation. Step 10 includes explicit validation commands (dry-run, kubeval, kube-score, kube-linter) with a testing checklist. The security section includes a checklist. The workflow has a logical dependency order (ConfigMap/Secret before Deployment). | 3 / 3 |
Progressive Disclosure | References external files (references/deployment-spec.md, references/service-spec.md, assets/*.yaml) which is good structure, but no bundle files are provided so these references are broken. The main file itself is monolithic with content that should be in those referenced files (e.g., the full security context YAML, troubleshooting, common patterns could all be separate). Significant inline content bloat that undermines the referencing strategy. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (535 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
34632bc
- 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.