CtrlK
BlogDocsLog inGet started
Tessl Logo

review-deps

Use when auditing the monorepo's dependencies — every workspace package.json — for version drift between workspaces and for upgrades available on npm. Finds the packages whose declared ranges disagree, checks the registry for newer versions, classifies each upgrade against the waiting-period rules, reads the changelogs of the ready ones, and reports the package.json changes to make.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exceptionally actionable, well-sequenced workflow skill with validation checkpoints covering network failure, batch edits, and report-shape integrity. The remaining gains are tightening a handful of rhetorical asides and offloading one or two self-contained blocks to reference files.

Suggestions

Trim editorial asides (e.g. 'a guess dressed as a fact', 'which is the run this report most often describes') to plain directives — the rules land the same without the framing.

Compress the Step 2 peerDependencies rationale to the rule itself ('report a peer range only when it is narrower than what a consumer declares') since the contract explanation restates what Claude already knows.

Move the verbatim DEPS-REVIEW.md heredoc template (or Step 5's changelog-source search order) into a references/ file and point to it, slimming the body while keeping the skeleton copy-exact.

DimensionReasoningScore

Conciseness

The body is command-first and lean ('Those four ## headings are the whole permitted set, in that order'), with almost no explanation of concepts Claude already knows. It is not a 5 because a few rhetorical flourishes ('a guess dressed as a fact') and the peerDependencies-as-contract explanation in Step 2 could be trimmed without losing guidance.

4 / 5

Actionability

Every step ships copy-paste-ready commands: the find/jq collection pipeline, the verbatim DEPS-REVIEW.md heredoc, the drift-detection one-liner, and the final grep checks that 'must print 4'. It matches the 5 anchor — fully executable guidance covering the common cases including the registry-unreachable case.

5 / 5

Workflow Clarity

Steps 0–7 are explicitly sequenced, an upfront probe ('git ls-remote... [ -d node_modules ]...') decides which steps run, and validation is woven throughout: 'Never write a version, a publish date or a Ready/Pending verdict you did not fetch', the frozen-lockfile check, the bun audit stop rule, and the closing heading-count check. This is a batch-edit workflow with explicit validation checkpoints and failure recovery, matching the 5 anchor.

5 / 5

Progressive Disclosure

The single file is well-sectioned with no nested or buried references, and no bundle files exist to mis-link. It is not a 5: at roughly 130 lines it exceeds the under-50-line simple-skill exception, and content such as the report template or Step 5's changelog-source search order could plausibly live in a separate reference file.

4 / 5

Total

18

/

20

Passed

Description

92%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: it states an explicit 'Use when' trigger with two concrete conditions and enumerates the full action pipeline in third person. The only improvement space is broader natural-language keyword coverage for the trigger scenario.

DimensionReasoningScore

Specificity

The description enumerates five concrete actions ('finds the packages whose declared ranges disagree, checks the registry for newer versions, classifies each upgrade against the waiting-period rules, reads the changelogs of the ready ones, and reports the package.json changes to make'), covering the workflow comprehensively in third-person voice. It matches the 5 anchor; it is not a 4 because there are no minor gaps in coverage of the task's actions.

5 / 5

Completeness

It opens with an explicit 'Use when auditing the monorepo's dependencies... for version drift between workspaces and for upgrades available on npm' clause with concrete trigger conditions, and the 'what' is a complete enumeration of the skill's actions. Both what and when are explicit, matching the 5 anchor; the 4 anchor ('when' could be more specific) does not apply since two precise trigger conditions are named.

5 / 5

Trigger Term Quality

Natural phrases like 'auditing the monorepo's dependencies', 'version drift between workspaces', and 'upgrades available on npm' are terms a user would plausibly say. It falls short of the 5 anchor because common variations such as 'outdated packages', 'update dependencies', or 'stale dependencies' are absent.

4 / 5

Distinctiveness Conflict Risk

The niche — auditing every workspace package.json in a monorepo for drift and npm upgrades under waiting-period rules — is distinct and would not fire for generic package-management or single-package update requests. It matches the 5 anchor with clear niche triggers and minimal conflict risk.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
englishstventures/osn
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.