Software Bill of Materials (SBOM) security analysis for vulnerability assessment and third-party risk management. Validates SBOMs from vendors or generates SBOMs for internal projects. Use this skill when: - User asks to analyze an SBOM file - User mentions "third-party risk" or "vendor security" - User needs to validate a supplier's SBOM - User wants to check SBOM for vulnerabilities - User asks about CycloneDX or SPDX formats
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 strong skill description that clearly defines its niche in SBOM security analysis. It provides specific capabilities, comprehensive trigger terms covering both natural language and technical formats, and an explicit 'Use this skill when' clause with well-defined scenarios. The description is concise, uses third-person voice, and would be easily distinguishable from other security-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions: 'security analysis for vulnerability assessment', 'third-party risk management', 'validates SBOMs from vendors', 'generates SBOMs for internal projects'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (SBOM security analysis, vulnerability assessment, validation, generation) and 'when' with an explicit 'Use this skill when:' clause listing five specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'SBOM', 'third-party risk', 'vendor security', 'supplier's SBOM', 'vulnerabilities', 'CycloneDX', 'SPDX formats'. These cover both common language and specific technical terms users in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on SBOM analysis specifically, with unique trigger terms like 'CycloneDX', 'SPDX', 'SBOM', and 'supplier's SBOM' that are unlikely to conflict with general security or vulnerability scanning skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with a clear multi-phase workflow for SBOM analysis, good error handling coverage, and useful reference tables. Its main weaknesses are that it's somewhat verbose for what Claude needs (report templates and vendor email templates could be much more concise or split out), and the validation phase lacks truly executable code, relying instead on descriptive checks and output templates. The workflow sequencing is the strongest aspect, with clear phases and validation checkpoints.
Suggestions
Replace the lengthy report templates with concise structural specs (e.g., 'Generate a table with columns: Component, Version, CVE, CVSS, Exploited') — Claude can format reports without full examples.
Add executable validation code (e.g., a Python snippet or jq command to check for missing purls) rather than just describing what fields to look for.
Move the vendor communication template and detailed report examples to a separate reference file (e.g., TEMPLATES.md) and link to it from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some verbosity that could be trimmed — the vendor communication template is lengthy, the report templates are quite detailed (Claude could generate these from a briefer spec), and some explanatory text like 'Core Principle: Know what's in your software supply chain' adds little value. However, the format tables and error handling sections are useful reference material. | 2 / 3 |
Actionability | The skill provides concrete tool calls (mcp_snyk_snyk_sbom_scan) and CLI commands for SBOM generation, which is good. However, the validation steps (Phase 1) lack executable code — they describe what to check but don't provide actual JSON parsing/validation code or jq commands. The report templates are output examples rather than executable guidance, and the scan tool calls use a non-standard function syntax that isn't clearly executable in any specific context. | 2 / 3 |
Workflow Clarity | The four-phase workflow (Validation → Security Scan → Risk Analysis → Remediation) is clearly sequenced with explicit sub-steps. Phase 1 includes validation before scanning, and the validation report template provides a clear checkpoint before proceeding. The error handling section covers common failure modes with recovery steps, creating effective feedback loops. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and phases, but it's a long monolithic document (~200+ lines of content) that could benefit from splitting detailed report templates, the vendor communication template, and error handling into separate reference files. Everything is inline with no references to supplementary materials. | 2 / 3 |
Total | 9 / 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.
adb5a9a
Table of Contents
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.