pantheon-ai/k8s-yaml-validator
Comprehensive toolkit for validating, linting, and testing Kubernetes YAML resources. Use this skill when validating Kubernetes manifests, debugging YAML syntax errors, performing dry-run tests on clusters, or working with Custom Resource Definitions (CRDs) that require documentation lookup.
Overall
score
93%
Does it follow best practices?
Validation for skill structure
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 well-crafted skill description that excels across all dimensions. It provides specific capabilities, uses natural trigger terms that Kubernetes users would actually say, includes an explicit 'Use this skill when...' clause with multiple scenarios, and carves out a clear niche that distinguishes it from general YAML or document processing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'validating, linting, and testing Kubernetes YAML resources', 'debugging YAML syntax errors', 'performing dry-run tests on clusters', 'working with Custom Resource Definitions (CRDs)'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('validating, linting, and testing Kubernetes YAML resources') and when ('Use this skill when validating Kubernetes manifests, debugging YAML syntax errors, performing dry-run tests on clusters, or working with Custom Resource Definitions'). Has explicit 'Use this skill when...' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Kubernetes', 'YAML', 'validating', 'linting', 'manifests', 'syntax errors', 'dry-run', 'CRDs', 'Custom Resource Definitions'. These are terms users naturally use when working with Kubernetes configurations. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Kubernetes YAML validation and testing. The combination of 'Kubernetes', 'manifests', 'CRDs', and 'dry-run tests' creates a distinct domain that wouldn't conflict with general YAML or document processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent workflow clarity, strong actionability through concrete commands and examples, and good progressive disclosure. The main weakness is moderate verbosity - some sections could be tightened without losing clarity, particularly the report structure examples and decision tree explanations.
Suggestions
Condense the 'Stage 6: Generate Detailed Validation Report' section - the example tables and format specifications are overly detailed for Claude's capabilities
Simplify the dry-run decision tree to a more compact format since Claude can infer the logic from fewer examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundant explanations (e.g., explaining what dry-run modes do, verbose decision trees). The report structure section is detailed but could be more concise since Claude understands markdown formatting. | 2 / 3 |
Actionability | Provides fully executable bash commands, specific tool invocations with exact flags, concrete JSON output examples, and copy-paste ready code blocks throughout. The workflow stages have clear, specific commands. | 3 / 3 |
Workflow Clarity | Excellent sequential workflow with 6 clearly numbered stages, explicit validation checkpoints, decision trees for error handling, and feedback loops (e.g., 'fix and re-validate'). The partial parsing behavior and error handling strategies are well-documented. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, conditional loading of reference files (k8s_best_practices.md, validation_workflow.md), and organized resources section. References are one level deep and clearly signaled with specific load conditions. | 3 / 3 |
Total | 11 / 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.
Install with Tessl CLI
npx tessl i pantheon-ai/k8s-yaml-validator@0.1.0Reviewed
Table of Contents