dependency-upgrade
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
68
54%
Does it follow best practices?
Impact
91%
1.05xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/framework-migration/skills/dependency-upgrade/SKILL.mdQuality
Discovery
82%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 a solid description that clearly communicates both what the skill does and when to use it, with good trigger term coverage for dependency upgrade scenarios. Its main weakness is that the capability descriptions are somewhat high-level ('compatibility analysis', 'staged rollout', 'comprehensive testing') rather than listing concrete specific actions, and it could potentially overlap with more general dependency management or testing skills.
Suggestions
Add more concrete specific actions like 'analyze changelogs for breaking API changes', 'update lock files', 'run codemods for deprecated APIs' to improve specificity.
Differentiate more clearly from general dependency management by specifying what makes this skill unique to *major* upgrades, e.g., mention migration guides, deprecation handling, or version pinning strategies.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dependency upgrades) and some actions (compatibility analysis, staged rollout, comprehensive testing), but these are somewhat high-level rather than concrete specific actions like 'update package.json', 'run migration scripts', or 'check API breaking changes'. | 2 / 3 |
Completeness | Clearly answers both 'what' (manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing) and 'when' (explicit 'Use when' clause covering upgrading framework versions, updating major dependencies, or managing breaking changes). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'dependency version upgrades', 'upgrading framework versions', 'updating major dependencies', 'breaking changes', 'libraries'. These cover common variations of how users would describe this task. | 3 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to major version upgrades, but could overlap with general dependency management skills, package management skills, or CI/CD testing skills. The focus on 'major' upgrades and 'breaking changes' helps distinguish it somewhat, but 'comprehensive testing' is broad enough to conflict. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose and tries to be a comprehensive reference document rather than a focused, actionable guide. It explains concepts Claude already knows (semver, what peer dependencies are), includes generic boilerplate code (test templates, CI configs), and dumps everything into a single file without progressive disclosure. The staged upgrade workflow has the right structure but lacks robust validation checkpoints and error recovery guidance.
Suggestions
Cut the semver review section entirely and remove generic test boilerplate (visual regression, E2E examples) — Claude knows how to write these. Focus only on upgrade-specific decision logic and gotchas.
Extract the compatibility matrix, automated update configs (Renovate/Dependabot), and testing strategy into separate referenced files to improve progressive disclosure.
Add explicit validation checkpoints with failure handling: what specifically to check after each upgrade step, what errors indicate incompatibility vs. fixable issues, and when to abort vs. continue.
Replace the incomplete `checkCompatibility` function and comment-only test assertions with actual executable validation logic or remove them entirely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and padded with content Claude already knows. The semver review section explains basic versioning concepts. The compatibility matrix is a hardcoded React-specific example that isn't generalizable. Many sections (visual regression tests, E2E tests, integration tests) show boilerplate test code that Claude can generate on its own. The entire file is ~250 lines when it could be under 80. | 1 / 3 |
Actionability | There are concrete commands and executable code snippets throughout (npm commands, config files, test examples), but much of it is generic boilerplate rather than targeted guidance. The compatibility-matrix.js has an empty `checkCompatibility` function, and the migration script uses naive regex replacements without caveats. The rollback script mixes bash and JavaScript comments incorrectly. | 2 / 3 |
Workflow Clarity | The staged upgrade strategy (Phase 1-3) provides a reasonable sequence, and the rollback plan includes a test-before-commit pattern. However, validation checkpoints are weak — Phase 3's validation tests have placeholder logic ('Run npm ls and check for warnings' as a comment). There's no explicit feedback loop for what to do when a mid-upgrade test fails beyond 'test again', and no guidance on partial rollback scenarios. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. Content like the full Renovate/Dependabot configs, the compatibility matrix, the migration script, and the testing strategy sections could all be split into separate reference files. Everything is inlined, making the skill overwhelming and hard to navigate. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- wshobson/agents
- Commit
27a7ed9
- 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.