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

Low

Low-risk findings worth noting

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 is highly actionable with a clearly sequenced staged-upgrade workflow and rollback loop, but it is padded with concepts Claude already knows and, most seriously, advertises seven bundle files that do not exist while duplicating that content inline.

Suggestions

Create the referenced bundle files (references/semver.md, references/compatibility-matrix.md, references/staged-upgrades.md, references/testing-strategy.md, assets/upgrade-checklist.md, assets/compatibility-matrix.csv, scripts/audit-dependencies.sh) or remove the Resources section — currently every link is broken.

Remove or relocate the inline Semantic Versioning Review explainer and the duplicated Upgrade Checklist / Best Practices / Common Pitfalls blocks to trim tokens and eliminate redundancy with the staged strategy.

Fill in the empty checkCompatibility function and replace placeholder args (<transform-url>, <path>) with concrete example values so all code is copy-paste executable.

DimensionReasoningScore

Conciseness

The "Semantic Versioning Review" section explains basic semver (^/~ meanings, MAJOR.MINOR.PATCH) Claude already knows, and the Upgrade Checklist, Best Practices, and Common Pitfalls sections overlap the staged strategy — mostly efficient but with unnecessary explanation that could be trimmed, fitting level 3 rather than the leaner level 4.

3 / 5

Actionability

Abundant executable commands and complete config files (renovate.json, dependabot.yml, rollback.sh, migration script) cover common cases; it falls short of level 5 because of the empty checkCompatibility function body and placeholder args like <transform-url> and <path> in the jscodeshift examples.

4 / 5

Workflow Clarity

The three-phase Staged Upgrade Strategy is clearly sequenced with test checkpoints after each increment and a rollback feedback loop, satisfying the validation requirement for batch operations; it is not level 5 because validation/retry is not woven explicitly into the main phased flow as a validate-fix-retry loop.

4 / 5

Progressive Disclosure

Section structure and a signaled Resources list are present, but the seven referenced files (references/*.md, assets/*, scripts/audit-dependencies.sh) do not exist and the semver, compatibility-matrix, staged-upgrades, and testing-strategy material is inlined while also being "referenced" — broken references plus duplication pull it below the well-organized level 4 anchor.

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.

The description is strong: concrete capabilities, an explicit Use-when clause with natural trigger phrases, and a clear niche. It is held back from a perfect profile only by slightly generic framing and missing synonyms.

DimensionReasoningScore

Specificity

Names the domain plus several concrete capabilities — "compatibility analysis", "staged rollout", and "comprehensive testing" alongside managing major upgrades — giving specific actions with only minor coverage gaps, which fits the level-4 anchor better than the 1-2 actions of level 3.

4 / 5

Completeness

It explicitly states both the "what" (manage upgrades with compatibility analysis, staged rollout, testing) and the "when" with multiple concrete trigger phrases, paralleling the level-5 example; it is not level 4 because the "when" is already explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

The "Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries" clause supplies natural phrases users actually say, with good coverage; it stops short of level 5 because synonyms like "bump", "migrate", or package-manager-specific terms are absent.

4 / 5

Distinctiveness Conflict Risk

The major-version-upgrade niche with breaking-change triggers is mostly distinct with only minor overlap risk against a generic dependency-management skill; it is not level 5 because "staged rollout" and the broad "manage upgrades" framing leave slight overlap with adjacent skills.

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.

Validation15 / 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.