linea-dependency-maintenance
Safely plan and execute JavaScript/TypeScript dependency maintenance across npm and pnpm repositories, including npm lockfiles, pnpm workspaces, catalogs, overrides, release-age policies, audits, CI validation, Dependabot boundaries, PRs, and GitHub tracking issues. Use whenever the user asks to update, bump, refresh, audit, clean, modernize, or review dependencies, reduce vulnerabilities, clean overrides, or prepare dependency PRs/issues.
92
92%
Does it follow best practices?
Impact
89%
1.00xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 an excellent skill description that clearly defines a specific niche (JS/TS dependency maintenance), lists comprehensive concrete capabilities, and provides explicit trigger guidance with natural user language. It uses proper third-person voice and covers both the 'what' and 'when' thoroughly. The only minor concern is that the description is somewhat dense, but the information density is justified by the breadth of the skill's capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: npm lockfiles, pnpm workspaces, catalogs, overrides, release-age policies, audits, CI validation, Dependabot boundaries, PRs, and GitHub tracking issues. This is highly specific and comprehensive. | 3 / 3 |
Completeness | Clearly answers both 'what' (plan and execute dependency maintenance across npm/pnpm repos with specific sub-tasks listed) and 'when' (explicit 'Use whenever the user asks to...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'update', 'bump', 'refresh', 'audit', 'clean', 'modernize', 'review dependencies', 'reduce vulnerabilities', 'clean overrides', 'dependency PRs/issues'. Also includes ecosystem terms like 'npm', 'pnpm', 'Dependabot', 'JavaScript/TypeScript'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: JavaScript/TypeScript dependency maintenance specifically for npm and pnpm ecosystems. The combination of specific package managers, lockfile types, pnpm workspaces/catalogs, and Dependabot makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides a clear multi-step workflow for dependency maintenance with concrete commands, explicit validation checkpoints, and appropriate progressive disclosure to reference files. Its main weakness is moderate verbosity in some sections—particularly the exhaustive enumeration of edge cases and repo-specific tooling in Validation and Tracking—though this verbosity is arguably justified by the complexity and risk of the domain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured and avoids explaining basic concepts, but some sections are verbose with enumeration of edge cases (e.g., the exhaustive list of repo-specific checks in Validation, the detailed PR template in Tracking). Some bullet points could be tightened without losing clarity. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for npm and pnpm (outdated, audit, explain, why), references a specific bundled script with exact CLI flags, and gives clear instructions for each phase. The triage classification categories are specific and actionable, and the apply/validation steps are concrete enough to follow directly. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Preflight → Policy → Inventory → Triage → Apply → Overrides → Validation → Tracking → Stop And Ask) with explicit validation checkpoints, feedback loops (revert and document if validation fails), and a clear 'Stop And Ask' gate for destructive/risky operations. The narrowest-to-broadest validation approach is a well-defined checkpoint strategy. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview workflow in the main file and explicitly references deeper materials at the end: `references/npm.md`, `references/pnpm.md`, and `scripts/eligible-updates`. References are one level deep and clearly signaled. The main content stays at the right level of abstraction for an overview. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- Consensys/linea-monorepo
- Commit
8ff65cd
- 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.