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.

1.05x

Quality

73%

Does it follow best practices?

Impact

91%

1.05x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/framework-migration/skills/dependency-upgrade/SKILL.md

Quality

Content

57%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 reference-heavy, code-dense body with strong executable commands but weak workflow checkpoints and no progressive disclosure. The staged rollout is present yet lacks explicit validation gates for a destructive/batch operation.

Suggestions

Make validation explicit and gate progression on it: after each incremental install, require a passing 'npm run test && npm run build' checkpoint with a fix-and-retry loop rather than a bare '# Test' comment.

Move the compatibility matrix and the Renovate/Dependabot config blocks into separate reference files (e.g. references/compatibility-matrix.json, references/renovate.json) and link to them one level deep, keeping SKILL.md as an overview.

Replace stub functions (checkCompatibility, the empty peer-dependency test) with real executable implementations or remove them, since placeholders pad tokens without adding actionability.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code/commands with no basic-concept padding, but several stub functions (checkCompatibility, empty peer-dep test) and the inlined compatibility matrix add length that does not earn its place.	3 / 5
Actionability	Predominantly executable commands and configs (npm-check-updates, jscodeshift with real transform URLs, renovate.json, dependabot.yml) with only minor gaps like the rollback script mislabeled in a javascript fence and a couple of stub bodies.	4 / 5
Workflow Clarity	A staged Phase 1/2/3 sequence with intervening test steps and a rollback feedback loop exists, but this is a batch/destructive operation and the per-step validation is implicit ('# Test', '# Test again') rather than explicit checkpoints; Phase 3 validation is a stub, so the destructive-skill cap applies.	3 / 5
Progressive Disclosure	Sections are well-headered but everything is inlined into one 365-line file with no bundle files; the compatibility matrix and config examples would benefit from being split into one-level-deep references.	3 / 5
	Total	13 / 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, well-constructed description that clearly states capability and explicit triggers in third-person voice. Minor keyword-coverage gaps keep trigger_term_quality and distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain plus multiple concrete actions — 'compatibility analysis, staged rollout, and comprehensive testing' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing') and when via a concrete 'Use when...' clause with three triggers.	5 / 5
Trigger Term Quality	Natural trigger phrases ('upgrading framework versions', 'updating major dependencies', 'managing breaking changes') give good keyword coverage, but a few common variants like 'bump dependency' or version-specific phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	The 'major dependency version upgrades' and 'breaking changes in libraries' niche is mostly distinct, with only minor overlap risk against general package-management skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/framework-migration/skills/dependency-upgrade/SKILL.md
Commit: d6837ae

Reviewed: about 12 hours 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.