CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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.

Excellent instructional content: a fully executable ten-stage validation pipeline with explicit sequencing, validation checkpoints, error-recovery fallbacks, and a well-organized one-level-deep bundle. The only improvement space is minor tightening of duplicated guidance between Philosophy, Anti-Patterns, and repeated reference pointers.

DimensionReasoningScore

Conciseness

The body is almost entirely executable commands, flags, and checklists with no concept explanations, but the Philosophy bullets restate several Anti-Patterns (read-only, continue-through-failures), template_functions.md is pointed to three times, and inline version pins like "1.28.0" could age — minor trim opportunities rather than padding, fitting the 'efficient; minor instances that could be trimmed' anchor.

4 / 5

Actionability

Every stage supplies copy-paste-ready commands with concrete flags (helm lint --strict, kubeconform with the full CRDs-catalog schema URL, exact grep checks), names MCP tools with parameters and a literal WebSearch query, and every referenced script/asset (setup_tools.sh, detect_crd_wrapper.sh, assets/.yamllint, etc.) exists in the bundle.

5 / 5

Workflow Clarity

Ten explicitly sequenced stages each perform a distinct validation, with a tool check first, continue-through-failure feedback loops, a mandatory Stage 10 report even on success, and an Error Handling section with concrete fallbacks — matching the anchor-5 pattern of clear sequence, explicit validation, and error-recovery guidance.

5 / 5

Progressive Disclosure

SKILL.md stays an overview/workflow while bulk detail lives in one-level-deep, clearly signaled references ("Read references/template_functions.md") that all exist, and a References section catalogs every bundle file for easy navigation — verified no nested references inside the reference files.

5 / 5

Total

19

/

20

Passed

Description

88%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 that clearly states both capabilities and trigger conditions in third person with concrete, domain-specific verbs. The only gaps are a few missing natural trigger variants and slight overlap risk with adjacent Kubernetes validation skills.

Suggestions

Add file-extension and command trigger terms users naturally mention, e.g. "Chart.yaml", "values.yaml", or "helm lint", to push trigger_term_quality toward comprehensive coverage.

Sharpen the boundary against adjacent skills by scoping the Kubernetes-resource language to chart output, e.g. "...analyzing the Kubernetes resources a chart renders (not plain manifests)".

DimensionReasoningScore

Specificity

"validating, linting, testing, and analyzing Helm charts and their rendered Kubernetes resources" plus "documentation lookup" for CRDs lists multiple concrete, domain-specific actions covering the tool's full capability set, matching the comprehensive-coverage anchor rather than the 'minor gaps' anchor below it.

5 / 5

Completeness

It explicitly answers 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, ... checking Helm best practices"), mirroring the anchor-5 exemplar's structure with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like "working with Helm charts", "validating templates", "debugging chart issues", and "Custom Resource Definitions (CRDs)" give good keyword coverage, but file-extension triggers (Chart.yaml, values.yaml) and tool-name phrases users actually say ("helm lint") are missing, so it fits 'good coverage, a few natural terms missing' rather than the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Helm charts is a clear niche, but "analyzing ... rendered Kubernetes resources" and "CRDs that require documentation lookup" could attract triggers for closely related plain-manifest or k8s-lint skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor.

4 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pantheon-org/tekhne

Path

skills/ci-cd/helm/validator/SKILL.md

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.