dependency-upgrade

Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches.

Quality

37%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/dependency-upgrade/SKILL.md

Quality

Content

38%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a broad reference document covering dependency upgrades but suffers from verbosity, explaining many concepts Claude already knows (semver, basic npm commands, what changelogs are). While it provides some concrete commands and configurations, many code examples are incomplete or placeholder-level. The content would benefit significantly from being trimmed to only novel, project-specific guidance and having its extensive inline examples moved to the referenced bundle files that don't actually exist.

Suggestions

Remove sections explaining concepts Claude already knows: semantic versioning basics, what changelogs are, generic best practices like 'read changelogs' and 'test thoroughly'. Focus on non-obvious guidance.

Complete placeholder code (empty `checkCompatibility` function, comment-only test) or remove them — incomplete examples reduce actionability without adding value.

Create the referenced bundle files (resources/implementation-playbook.md, references/compatibility-matrix.md, etc.) and move the detailed examples, configs, and matrices into them, keeping SKILL.md as a concise overview.

Add explicit validation checkpoints with feedback loops in the staged upgrade workflow, e.g., 'If build fails after React upgrade: check migration guide for API changes, apply codemods, re-run build before proceeding.'

Dimension	Reasoning	Score
Conciseness	Significantly verbose with many sections that explain concepts Claude already knows (semantic versioning, what changelogs are, basic npm commands). The compatibility matrix JavaScript example is largely placeholder code. Best practices and common pitfalls sections are generic advice Claude doesn't need. The skill could be cut by 60%+ without losing actionable value.	2 / 5
Actionability	Contains concrete commands and code snippets (npm audit, codemods, Renovate/Dependabot configs), but many examples are incomplete or semi-pseudocode (e.g., `checkCompatibility` function is empty, the compatibility test has a comment instead of implementation). The migration script is a simplistic find-replace that wouldn't work well in practice.	3 / 5
Workflow Clarity	The staged upgrade strategy has a reasonable 3-phase structure with test steps between upgrades, and the rollback plan includes a conditional check. However, validation is mostly just 'npm run test' without explicit checkpoints for what to do when tests fail beyond the rollback script. The upgrade checklist is helpful but separated from the workflow, and there's no explicit feedback loop for fixing breaking changes during the incremental upgrade process.	3 / 5
Progressive Disclosure	The skill references multiple resource files (references/semver.md, assets/upgrade-checklist.md, scripts/audit-dependencies.sh, resources/implementation-playbook.md) but no bundle files are provided, meaning none of these references resolve. The main file is a monolithic ~300-line document that inlines extensive content (compatibility matrices, full test examples, config files) that should be in separate referenced files.	2 / 5
	Total	10 / 20 Passed

Description

36%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 identifies a clear domain (dependency version upgrades) but relies on abstract, high-level language rather than concrete actions. It lacks a 'Use when...' clause entirely, making it difficult for Claude to know when to select this skill. The trigger terms are too generic and miss natural user language around package management and upgrades.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases like 'Use when the user asks about updating packages, resolving breaking changes, upgrading major versions, or dealing with outdated dependencies.'

Replace abstract categories with specific actions, e.g., 'Analyzes breaking changes between major versions, creates staged migration plans, updates dependency configurations, and resolves compatibility conflicts.'

Include natural keywords and synonyms users would say, such as 'npm update', 'package upgrades', 'outdated packages', 'breaking changes', 'migration', 'semver', or specific ecosystem terms.

Dimension	Reasoning	Score
Specificity	Names the domain (dependency version upgrades) but the actions listed are vague and abstract — 'compatibility analysis', 'staged upgrade strategies', and 'comprehensive testing approaches' are high-level categories rather than concrete actions like 'update package.json', 'resolve breaking changes', or 'run migration scripts'.	2 / 5
Completeness	Provides a vague 'what' (master dependency upgrades and related activities) but has no 'when' clause at all. There is no explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and the weak 'what' brings it to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'dependency', 'version upgrades', and 'compatibility', but misses natural user phrases like 'update packages', 'npm upgrade', 'breaking changes', 'semver', 'outdated dependencies', or specific package manager names.	3 / 5
Distinctiveness Conflict Risk	Somewhat specific to dependency upgrades, which narrows the domain, but 'compatibility analysis' and 'testing approaches' are broad enough to overlap with general testing skills or code analysis skills. The lack of specific technology or ecosystem references increases overlap risk.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/dependency-upgrade/SKILL.md
Commit: 57c135b

Reviewed: 3 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.