dependency-auditor

Audit and manage dependencies across multi-language projects. Identifies vulnerabilities, license conflicts, transitive dependency risks, and safe-upgrade paths. Use when auditing third-party packages before release, investigating a CVE, planning a major version bump, or running a license-compliance review. Examples: 'audit our npm dependencies', 'do we have GPL contamination', 'plan the upgrade to React 19'.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

78%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.

The body is highly actionable with executable commands and a clear workflow plus validation loop, but progressive disclosure is weakened by references to files that do not exist in the bundle. Conciseness and workflow clarity are strong with only minor gaps.

Suggestions

Remove or correct references to missing bundle paths (README.md, test-project/, test-inventory.json, expected_outputs/), or add those files so navigation links resolve.

Link the individual reference files in references/ (e.g. vulnerability_assessment_guide.md, license_compatibility_matrix.md) instead of naming the directory generically, so the one-level-deep pointers are concrete.

Add a short error-recovery branch to the verification loop (e.g. what to do when a re-scan still reports high-severity findings) to strengthen the workflow's feedback path.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly lean — tables and executable commands assume Claude's competence rather than explaining basics — but the 'Best Practices' list and the 'Scripts (accurate capability claims)' framing add minor padding that could be trimmed.	4 / 5
Actionability	Quick Start provides fully executable, copy-paste-ready commands with concrete flags (--fail-on-high, --policy strict, --risk-threshold medium) and named output files, covering the three common cases.	5 / 5
Workflow Clarity	A clear three-step sequence is present with an explicit validation checkpoint ('after applying upgrades, re-run step 1 and assert 0 high-severity findings before closing the audit'), but error-recovery detail on a failed scan is thin.	4 / 5
Progressive Disclosure	Structure and sectioning are good, but referenced paths are partly broken: the body links to README.md and mentions test-project/, test-inventory.json, and expected_outputs/, none of which exist in the bundle, while references/ (which does exist with three files) is only named generically rather than linked.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

The description is exemplary: it pairs a comprehensive list of concrete capabilities with an explicit 'Use when' clause and natural-language example triggers, all in third person. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Identifies vulnerabilities, license conflicts, transitive dependency risks, and safe-upgrade paths' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (audits deps, identifies vulnerabilities/license conflicts/upgrade paths) and 'when' ('Use when auditing third-party packages before release, investigating a CVE, planning a major version bump, or running a license-compliance review') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases are included verbatim as examples — 'audit our npm dependencies', 'do we have GPL contamination', 'plan the upgrade to React 19' — alongside triggers like 'investigating a CVE' and 'planning a major version bump'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear dependency-auditing/security niche with distinct triggers ('GPL contamination', 'major version bump'); minimal overlap risk with unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering/skills/dependency-auditor/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

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.