CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/checkov-policy

Use for any question or task about Checkov or scanning infrastructure code (Terraform, CloudFormation, Kubernetes, Helm, ARM, Serverless, CDK) with the broadest built-in rule set, including custom security checks written in Python: SARIF and JUnit output, and a baseline so CI fails only on new findings. Single-tool option: trivy-config.

Quality

81%

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

Overview
Quality
Evals
Security
Files

Quality

Content

71%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 well-structured, highly actionable body with copy-paste commands for every common case, a concrete worked example, and exemplary use of a one-level-deep reference file. The main costs are token efficiency: a redundant step-summary list and an inline pinned version number that will age.

Suggestions

Remove the 'How to use' 7-item list (or compress it to one line per phase) — it duplicates the Step 1-9 section headings it cross-references.

Drop the pinned literal 'checkov==3.2.500' from Step 1 and the worked example, or move version guidance to a dedicated note, since inline version numbers go stale and the rubric penalizes them outside deprecated/old-patterns sections.

Make Step 9 concrete: either show an executable command (or small script) that merges the checkov/tfsec/kics JSON reports into a unified verdict, or move multi-scanner combination detail into the references file.

DimensionReasoningScore

Conciseness

Mostly efficient command-focused content with no concept padding, but the 7-item 'How to use' list duplicates the step sections, and the time-sensitive version literal 'checkov==3.2.500' appears in Step 1 and the worked example outside any deprecated/old-patterns section — the rubric explicitly penalizes inline version numbers. Could be tightened to earn 4.

3 / 5

Actionability

Nearly all guidance is copy-paste ready ('checkov -d . --framework terraform,kubernetes,dockerfile', '-o sarif --output-file-path checkov.sarif', '--create-baseline', the 'checkov:skip=CKV_AWS_20:' HCL annotation), with executable Python and CI YAML verified in references/custom-checks-and-ci.md. Falls short of 5 only because Step 9's '# Combine the three reports into a unified verdict' is a non-executable placeholder.

4 / 5

Workflow Clarity

A clear 9-step sequence with install verification ('checkov --version'), an explicit triage step, and a worked example containing a real feedback loop (new finding → fix or justified skip → build green). Not 5 because validation checkpoints are implicit in the steps themselves rather than spelled out as explicit verify steps outside the worked example.

4 / 5

Progressive Disclosure

Verified against the actual bundle: one real reference file (references/custom-checks-and-ci.md), one level deep, clearly signaled with markdown links at exactly the right points (Step 5 and Step 8); the heavy custom-check Python and CI YAML correctly live in the reference rather than the body, and sections are well-organized for navigation.

5 / 5

Total

16

/

20

Passed

Description

83%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 an explicit 'Use for...' trigger clause, concrete framework-specific triggers, and clearly stated capabilities (custom Python checks, SARIF/JUnit output, baseline gating). Its main weaknesses are slightly tangled syntax around the capability list and a cryptic sister-tool cross-reference that mildly blurs distinctiveness.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — 'scanning infrastructure code (Terraform, CloudFormation, Kubernetes, Helm, ARM, Serverless, CDK)', 'custom security checks written in Python', 'SARIF and JUnit output', 'a baseline so CI fails only on new findings' — but the tangled 'with the broadest built-in rule set, including...: SARIF and JUnit output' syntax obscures the action list, keeping it below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers both: the when is 'Use for any question or task about Checkov or scanning infrastructure code (...)' with concrete triggers, and the what covers scanning across named frameworks, custom Python checks, SARIF/JUnit output, and baseline gating. Not 4 because the when-clause is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Strong natural keywords: 'Checkov' plus the framework names users would actually say (Terraform, CloudFormation, Kubernetes, Helm), along with 'SARIF', 'JUnit', 'baseline', 'CI'. Missing the phrase 'infrastructure as code'/'IaC', 'misconfiguration', and file extensions like .tf, so it falls just short of the comprehensive-synonym 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'Checkov' plus the named frameworks carve a clear niche with distinct triggers, but the trailing 'Single-tool option: trivy-config' cross-references a sister scanner, creating minor overlap/confusion risk with closely related skills. Not 3 because the domain is specific, not merely 'somewhat specific'.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page