CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

linea-dependency-maintenance

Safely plan and execute dependency maintenance for JavaScript/TypeScript (npm, pnpm) and GitHub Actions, including npm lockfiles, pnpm workspaces, catalogs, overrides, SHA-pinned action versions, 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 or GitHub Actions, reduce vulnerabilities, clean overrides, or prepare dependency PRs/issues.

1.45x
Quality

88%

Does it follow best practices?

Impact

90%

1.45x

1 of 3 eval scenarios. Add 2 more for a full score.

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-structured, highly actionable skill whose multi-phase workflow, validation checkpoints, and one-level-deep reference layout are exemplary. Its main weakness is token efficiency: the maturity-gate policy is repeated many times and a few sections could be tightened without losing clarity.

Suggestions

State the release-age/maturity-gate rule once in Policy as a hard gate with its rationales, and have Apply and Overrides reference it ('per the maturity gate in Policy') instead of restating it five-plus times with variations like 'hard gate, not a hurdle to bypass' and 'not a suggestion'.

Trim conceptual explanations Claude already knows, e.g. 'peerDependencies: those declare the version range a consumer must satisfy (the package never installs them itself)' — keep only the operative rule (leave intentional peer ranges as ranges).

Consolidate the two long Overrides paragraphs about pnpm's in-window fallback behavior into a single step in the numbered refresh flow, moving the pnpm-10-specific detail to references/pnpm.md where the per-manager commands already live.

DimensionReasoningScore

Conciseness

The body is mostly high-value operational guidance, but the release-age maturity-gate rule is restated five or six times across Policy, Apply, and Overrides ('hard gate, not a hurdle to bypass', 'not a suggestion', 'Do not bypass minimumReleaseAge', 'never widen minimumReleaseAgeExclude', 'revert it'), and it briefly explains concepts like peerDependencies semantics — noticeable tightening opportunities beyond minor over-explanation.

3 / 5

Actionability

Guidance is fully executable: concrete commands ('npm outdated --json', 'node <skill-dir>/scripts/eligible-updates --manager auto --days 3', 'pnpm audit --fix'), a copy-paste-ready SHA-bump diff example, specific commit-message formats, and per-manager command details verified to exist in the bundled reference files.

5 / 5

Workflow Clarity

The workflow is clearly sequenced (Preflight → Inventory → Triage → Apply → Overrides → Validation → PR) with an explicit triage checklist, validation ordered by blast radius, and genuine feedback loops such as 'If a supposedly safe update breaks validation, revert just that candidate and document why' plus conflicting-pin reconciliation before bumping.

5 / 5

Progressive Disclosure

The SKILL.md carries the workflow and policy while per-manager commands and gh SHA-resolution details are split one level deep into references/npm.md, references/pnpm.md, and references/github-actions.md (all present on disk), each signaled at its point of use and recapitulated in an 'Additional Resources' section, with both bundled scripts invoked with example args.

5 / 5

Total

18

/

20

Passed

Description

88%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 description that clearly states a comprehensive set of concrete capabilities and pairs it with an explicit, natural-language trigger clause. The only weaknesses are a few missing common trigger synonyms ('upgrade', 'outdated') and slight overlap risk with generic security/audit skills.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities — 'npm lockfiles, pnpm workspaces, catalogs, overrides, SHA-pinned action versions, release-age policies, audits, CI validation, Dependabot boundaries, PRs, and GitHub tracking issues' — giving comprehensive coverage of the dependency-maintenance domain rather than just a few actions.

5 / 5

Completeness

It explicitly answers both 'what' (the first sentence's concrete capability list) and 'when' ('Use whenever the user asks to update, bump, refresh, audit...') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Trigger verbs are natural and varied ('update, bump, refresh, audit, clean, modernize, or review dependencies') plus goal-oriented phrases ('reduce vulnerabilities, clean overrides, or prepare dependency PRs/issues'), but common user variations like 'upgrade' and 'outdated' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche is clear and specific (npm/pnpm ecosystems plus SHA-pinned GitHub Actions), but phrases like 'audit' and 'reduce vulnerabilities' create minor overlap risk with general security-audit or code-review skills rather than minimal conflict risk.

4 / 5

Total

18

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

LFDT-Lineth/lineth-monorepo

Path

.agents/skills/linea-dependency-maintenance/SKILL.md

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.