node-modules-inspector

Inspects a project's installed node_modules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate packages, check what's taking up disk space in node_modules, identify outdated peer/prod dependencies that newer dependents could upgrade past, or list publint problems. Available as a CLI (`npx node-modules-inspector report <duplicates|sizes|maintainers> [--json]`) or an MCP stdio server (`npx node-modules-inspector mcp`) exposing the same three reports as agent tools. Works with pnpm, npm, and bun.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%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 high-quality, action-dense body: executable commands, complete JSON output shapes, and clear failure-mode guidance, with only minor room to formalize the multi-step workflow sequencing.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — assumes Claude knows semver/publint/node_modules concepts; no padding, every section (commands, JSON output shapes, flags, failure modes) earns its place.	5 / 5
Actionability	Fully executable — copy-paste `npx node-modules-inspector report <subcommand> --json` commands for every report, complete JSON output shapes with all fields, and exact option flags with defaults covering all common cases.	5 / 5
Workflow Clarity	Clear per-report workflow with a strong 'Failure modes' section giving interpretation guidance for empty/error results, but the read-only inspection flow is presented per-report rather than as one explicitly sequenced multi-step path with checkpoints.	4 / 5
Progressive Disclosure	Well-organized into clearly-labeled sections (When to reach, CLI mode, MCP mode, Flags, Failure modes, Web UI); no bundle files exist and none are referenced, and the inline JSON schemas are justified since the agent needs exact output shapes for validation.	5 / 5
	Total	19 / 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.

A strong, specific description that clearly states what the skill does (three node_modules reports via CLI/MCP) and when to use it, with comprehensive natural trigger phrases and a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Inspects a project's installed node_modules and produces three reports: duplicated packages... install size... maintenance actions' — with comprehensive coverage of each report and the CLI/MCP surface.	5 / 5
Completeness	Explicitly answers both what (three reports, CLI + MCP, pnpm/npm/bun) and when ('Use when the user wants to audit dependencies, find duplicate packages...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers with synonyms — 'audit my dependencies', 'find duplicate packages', 'node_modules cleanup', 'what's taking up disk space in node_modules', 'which deps are outdated', 'show me publint issues', 'who maintains my dependencies'.	5 / 5
Distinctiveness Conflict Risk	Clear niche — on-disk node_modules inspection producing three specific named reports — with distinct triggers and minimal overlap risk; the body further distinguishes it from npm audit / osv-scanner / fast-npm-meta.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: antfu/node-modules-inspector
Path: skills/node-modules-inspector/SKILL.md
Commit: f5d3d6f

Reviewed: 13 days 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.