CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

78

1.75x
Quality

73%

Does it follow best practices?

Impact

79%

1.75x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/framework-migration/skills/dependency-upgrade/SKILL.md

The canonical home for this skill is dependency-upgrade in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

The body delivers strong executable guidance for staged dependency upgrades, including validation and rollback flows. Its weaknesses are redundancy (semver primer, restated description), a few stub code blocks, and a Resources section pointing entirely at bundle files that do not exist while duplicating their content inline.

Suggestions

Delete the "Semantic Versioning Review" section and the "When to Use This Skill" list — both restate knowledge Claude already has or the frontmatter description already covers.

Create the referenced bundle files (references/semver.md, assets/upgrade-checklist.md, etc.) or remove the Resources section; currently all seven listed paths are broken, and the inline compatibility matrix and upgrade checklist duplicate them.

Complete or remove the stubbed code: checkCompatibility() has no implementation, the peer-dependency test is a comment, and rollback.sh is mislabeled as a javascript block.

DimensionReasoningScore

Conciseness

The "Semantic Versioning Review" section re-explains MAJOR.MINOR.PATCH and ^/~ ranges — concepts Claude already knows — and the intro plus "When to Use This Skill" list largely restate the frontmatter description. Much of the rest (commands, configs, scripts) is efficient, so it sits between the padded 2 anchor and the trim 4 anchor.

3 / 5

Actionability

Mostly executable: concrete npm/yarn/jscodeshift commands, a runnable migration script, complete renovate.json and dependabot.yml, and a working rollback script. Not a 5 because of stubs and gaps — checkCompatibility() is an empty function with only a comment, the peer-dependency test is a comment placeholder, and the rollback script is fenced as ```javascript though it is bash.

4 / 5

Workflow Clarity

The staged upgrade strategy (Phase 1 planning, Phase 2 one-package-at-a-time with "Test again" after each step, Phase 3 validation) plus a rollback script with a test-then-revert feedback loop and a pre/during/post checklist gives a clear sequence with most checkpoints. Not a 5 because Phase 3's validation test is itself a stub ("// Run npm ls and check for warnings") and some checkpoints are implicit.

4 / 5

Progressive Disclosure

Section structure is clear and the Resources section lists bundle files with descriptions, but none of the seven referenced files (references/*.md, assets/*, scripts/audit-dependencies.sh) actually exist, and the body inlines ~400 lines of content (semver guide, compatibility matrix, upgrade checklist) that duplicates those supposed files. This fits the 3 anchor (content that should be separate is inline, references not fully trustworthy) rather than 2, since headers and the reference list are well organized.

3 / 5

Total

14

/

20

Passed

Description

83%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: third-person voice, concrete capabilities, and an explicit 'Use when...' clause with natural trigger phrases. The only gap is the absence of ecosystem-specific synonyms (npm, package.json, bump) that would make triggering even more reliable.

DimensionReasoningScore

Specificity

Names the domain ("major dependency version upgrades") and several concrete capabilities ("compatibility analysis, staged rollout, and comprehensive testing"). Not a 5 because "comprehensive testing" is generic and the capability list is thinner than the multi-action 5 anchor; not a 3 because more than 1-2 concrete actions are explicitly stated.

4 / 5

Completeness

Explicitly answers both: what ("Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing") and when ("Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries") with concrete trigger phrases, matching the 5 anchor's structure.

5 / 5

Trigger Term Quality

"upgrading framework versions", "updating major dependencies", and "managing breaking changes" are phrases users would naturally say. Not a 5 because ecosystem-specific terms users actually use (npm, package.json, bump versions, upgrade packages) and synonyms are missing; clearly above the partial-coverage 3 anchor.

4 / 5

Distinctiveness Conflict Risk

"Major dependency version upgrades" and "breaking changes" carve a clear niche distinct from general package-management or build skills. Not a 5 because it is tool-agnostic, so it could overlap with runtime/version-manager or general npm-maintenance skills; well above the broad-overlap 2-3 anchors.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 7 missing

Warning

Total

15

/

16

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.