CtrlK
BlogDocsLog inGet started
Tessl Logo

fusion-dependency-review

Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation.

63

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and assumes Claude's competence without padding, but it duplicates its orchestration steps and its core execution path depends on advisor files that are absent from the bundle. Fixing the missing `agents/` references and collapsing the two orchestration summaries would lift it to top marks.

Suggestions

Add the seven missing `agents/*.md` files (or remove the advisor references and inline their guidance) so the primary execution path is real rather than dangling.

Merge the "Preferred advisor orchestration" and "Workflow summary" sections into one sequenced list to remove the duplicated orchestration tokens.

Inline at least one explicit validate→fix→retry checkpoint (e.g. for branch rebase or merge-readiness) in the main workflow rather than deferring all feedback loops to references/instructions.md.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but "Preferred advisor orchestration" (5 steps) and "Workflow summary" (6 steps) restate the same orchestration twice, adding tokens that could be consolidated.

2 / 3

Actionability

Concrete asset/reference paths and a fully specified output structure are present, but the primary execution path leans on seven `agents/*.md` files that do not exist in the bundle, and the inline fallback ("research first, lenses next, verdict after that") stays abstract.

2 / 3

Workflow Clarity

Steps are clearly sequenced and checkpoints are named (research checkpoint comment, final verdict comment), but for a mutation-capable skill the validate→fix→retry feedback loops are offloaded to references rather than shown inline, which caps clarity at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Structure is one level deep with clearly signaled Assets/References/Advisors sections, but seven `agents/*.md` references are dangling (files missing from the bundle), so navigation is partially broken despite good organization.

2 / 3

Total

8

/

12

Passed

Description

100%

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 concrete, third-person, and supplies explicit positive and negative triggers, hitting every anchor at the top of the scale. It is concise yet complete, with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template" — matching the score-3 anchor rather than the single-action score-2 anchor.

3 / 3

Completeness

Explicitly answers both what (the review activities) and when via a "USE FOR:" clause plus a "DO NOT USE FOR:" exclusion list, satisfying the explicit-trigger requirement that caps completeness at 2 when absent.

3 / 3

Trigger Term Quality

Covers natural terms a user would say — "dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, 'review this dependency PR', 'should we merge this update'" — with good variation including bot names and quoted phrasings.

3 / 3

Distinctiveness Conflict Risk

Clear niche (dependency update PRs) with a distinct "DO NOT USE FOR: feature PRs, application code reviews" boundary, making conflict with adjacent code-review skills unlikely.

3 / 3

Total

12

/

12

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

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
equinor/fusion-framework
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.