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.
69
58%
Does it follow best practices?
Impact
79%
1.75xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 (e.g., 'compatibility analysis', 'staged rollout') rather than listing granular concrete actions, and there's some potential overlap with adjacent skills around testing and package management.
Suggestions
Make capabilities more concrete by specifying actions like 'analyze changelogs for breaking API changes', 'update dependency lock files', 'generate migration guides', or 'run compatibility test suites'.
Add more distinctive trigger terms or file types (e.g., 'package.json', 'Gemfile', 'semver', 'migration') to reduce potential overlap with general testing or CI/CD skills.
| 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 listing multiple concrete specific actions like 'update package.json', 'run migration scripts', '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 phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to major version upgrades and breaking changes, but could overlap with general package management skills, CI/CD skills, or 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
35%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 guide rather than a focused, actionable skill for Claude. It explains concepts Claude already knows (semver, what unit/integration/E2E tests are), includes incomplete code stubs, and packs too much generic content inline. The staged upgrade workflow is the strongest section but still lacks robust validation checkpoints and error recovery loops.
Suggestions
Remove explanations of concepts Claude already knows (semver basics, what different test types are, what lock files do) to cut content by ~40%
Complete the stub implementations (checkCompatibility function, peer dependency test) or remove them — incomplete code reduces actionability
Move the compatibility matrix, testing examples, and automation configs into separate referenced files to improve progressive disclosure and reduce SKILL.md length
Add explicit validation checkpoints with feedback loops in the staged upgrade workflow, e.g., 'If build fails after React upgrade: check peer deps with npm ls, resolve conflicts, re-run build before proceeding'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. Explains semver (Claude knows this), includes a compatibility matrix stub with empty function, lists obvious best practices ('Read Changelogs'), and repeats testing concepts Claude already understands. The 'When to Use This Skill' section is unnecessary padding. Much of this content (visual regression tests, E2E tests, integration tests) is generic boilerplate that doesn't add value. | 1 / 3 |
Actionability | Provides concrete commands (npm outdated, npx jscodeshift) and executable code snippets, but many examples are incomplete or generic. The compatibility matrix has an empty checkCompatibility function, the migration script uses naive regex replacements, and the rollback script mixes bash and JavaScript comments incorrectly. Several code blocks are illustrative rather than truly copy-paste ready. | 2 / 3 |
Workflow Clarity | The staged upgrade strategy (Phase 1-3) provides a reasonable sequence, and the upgrade checklist is helpful. However, validation checkpoints are weak — Phase 3 validation tests are stubs (the peer dependency test has a comment instead of implementation). There's no explicit feedback loop for handling failures during the staged upgrade beyond the rollback script, and the rollback script itself has issues (uses bash shebang but is named .js in the section). | 2 / 3 |
Progressive Disclosure | References to external files (references/semver.md, assets/upgrade-checklist.md, scripts/audit-dependencies.sh) are listed in the Resources section, but no bundle files exist to support them. The SKILL.md itself is monolithic — over 300 lines of inline content that could be split into separate reference files for the compatibility matrix, testing strategy, and automation configs. | 2 / 3 |
Total | 7 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
b09ec7f
- 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.