CtrlK
BlogDocsLog inGet started
Tessl Logo

helm-validator

Comprehensive toolkit for validating, linting, testing, and analyzing Helm charts and their rendered Kubernetes resources. Use this skill when working with Helm charts, validating templates, debugging chart issues, working with Custom Resource Definitions (CRDs) that require documentation lookup, or checking Helm best practices.

73

Quality

90%

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

92%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.

An excellent read-only validation skill: a fully executable ten-stage workflow with embedded validation checkpoints, error-recovery guidance, and a mandatory reporting step, backed by a real bundle whose details are properly deferred to one-level-deep references. The only notable weakness is minor token redundancy in the overview, the repeated template_functions.md pointers, and the trailing file catalog.

DimensionReasoningScore

Conciseness

The body is dominated by exact commands and checklists with no explanations of concepts Claude already knows, but there is minor padding: the Overview restates the description, references/template_functions.md is pointed to three separate times in one section, and the trailing file catalog duplicates the inline pointers.

4 / 5

Actionability

Every stage gives copy-paste-ready commands with exact flags (helm lint --strict, the full kubeconform -schema-location URL, grep checks for securityContext/:latest), plus a concrete JSON output example and executable script invocations, fully covering the common cases.

5 / 5

Workflow Clarity

Ten explicitly sequenced stages each carry their own validation (lint, yamllint, kubeconform, dry-run), an Error Handling section gives per-failure fallbacks and feedback loops ('fix in the source template — not the rendered output', 'continue to next stage, collect all errors'), and a mandatory final report checklist closes the loop.

5 / 5

Progressive Disclosure

The body is a clear overview that signals one-level-deep references on demand ('Load References (when issues found)', 'For complex templating tasks, load the dedicated reference'), all referenced bundle paths exist, and the bulk detail (template functions, Helm/K8s best practices) is correctly split into separate files with a closing catalog for navigation.

5 / 5

Total

19

/

20

Passed

Description

87%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 with a clear what-clause and an explicit, well-populated 'Use this skill when...' trigger list covering the Helm validation domain. Minor room to improve by tightening generic verbs ('testing', 'analyzing') into concrete capabilities and adding a few more natural synonyms such as 'helm lint' or 'Kubernetes manifests'.

Suggestions

Replace the generic verbs 'testing' and 'analyzing' with the concrete capabilities the skill actually performs (e.g. 'rendering templates and validating them against Kubernetes schemas').

Drop the filler opener 'Comprehensive toolkit for' and lead directly with the actions to save description tokens.

Add one or two natural trigger synonyms users commonly say, such as 'helm lint fails' or 'Kubernetes manifest validation'.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("validating, linting, testing, and analyzing Helm charts and their rendered Kubernetes resources") plus CRD documentation lookup, but "testing" and "analyzing" remain somewhat generic and "Comprehensive toolkit" is light filler, leaving minor gaps versus the comprehensive-coverage anchor.

4 / 5

Completeness

It explicitly answers both what ("validating, linting, testing, and analyzing Helm charts and their rendered Kubernetes resources") and when ("Use this skill when working with Helm charts, validating templates, debugging chart issues..."), matching the anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like "working with Helm charts", "validating templates", "debugging chart issues", and "Helm best practices" are present, though a few common variations users would say (e.g. "helm lint", "Kubernetes manifests/YAML", "helm release") are missing.

4 / 5

Distinctiveness Conflict Risk

The Helm-chart niche is clearly staked out with distinct, domain-specific triggers (charts, templates, CRDs, Helm best practices), making conflicts with other skills unlikely.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pantheon-org/tekhne
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.