CtrlK
BlogDocsLog inGet started
Tessl Logo

vulnerability-scanning

Automated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit. Use for CI/CD security gates, pre-deployment audits, compliance requirements, or encountering CVE detection, outdated packages, license compliance, SBOM generation errors.

75

Quality

93%

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

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable reference of executable scanning commands and a CI integration, well-organized into clear sections. Its main weakness is workflow clarity: it presents a toolkit of scans rather than a sequenced process with explicit validation checkpoints.

Suggestions

Add a short numbered "Scanning workflow" section that sequences the scans (e.g. dependency → container → code) with an explicit validation/exit-code checkpoint after each, plus a fix-and-reretry note for findings.

In the GitHub Actions example, call out the exit-code behavior (Trivy exit-code: '1', npm audit --audit-level=high) as an explicit pass/fail gate so the validation step is signaled rather than implicit.

Tighten the "Best Practices" and "Tools" lists, which partially restate what the code examples already demonstrate, to remove mild redundancy.

DimensionReasoningScore

Conciseness

The body is mostly copy-paste code snippets with minimal prose and no padding explaining concepts Claude already knows; the only comments justify non-obvious error handling. It is lean and every section is short.

3 / 3

Actionability

Commands and snippets are concrete and executable (e.g. "trivy image myapp:latest --severity HIGH,CRITICAL", "bandit -r src/ -ll -ii", a full GitHub Actions YAML), copy-paste ready with specific flags.

3 / 3

Workflow Clarity

The body is organized by scan type rather than as a sequenced process, and the GitHub Actions YAML is the only near-sequence; it lacks explicit validation checkpoints or a validate→fix→retry feedback loop, matching the anchor with steps present but checkpoints missing.

2 / 3

Progressive Disclosure

No bundle files exist and the body is well-organized into clearly headed sections (Dependency, Container, CI, Code, Best Practices, Tools) with no nested or multi-level references, satisfying the well-organized-sections case for a self-contained skill.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that pairs a concrete capability statement with an explicit "Use for ..." trigger clause covering natural user terms. It is specific, complete, and clearly niche-distinguished with no over-claims or padding.

DimensionReasoningScore

Specificity

Lists multiple concrete scanning targets ("dependencies, code, containers") and names specific tools ("Trivy, Snyk, npm audit") plus SBOM and license compliance, matching the anchor for multiple specific concrete actions rather than a single vague domain.

3 / 3

Completeness

It explicitly answers both what ("Automated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit") and when (an explicit "Use for ..." clause with concrete triggers), satisfying the top anchor.

3 / 3

Trigger Term Quality

The "Use for ... CI/CD security gates, pre-deployment audits, compliance requirements, or encountering CVE detection, outdated packages, license compliance, SBOM generation errors" clause covers natural terms a user would actually say, with good breadth of variations.

3 / 3

Distinctiveness Conflict Risk

Vulnerability/SCA scanning is a clear niche with distinct triggers (CVE, SBOM, Trivy, pre-deployment audit) that are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
secondsky/claude-skills
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.