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.

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/fusion-dependency-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 well-structured with explicit safety gates and clear sequencing, but it triplicates the orchestration narrative and — more seriously — anchors its primary execution path on seven advisor files that are missing from the bundle, undercutting both actionability and navigation.

Suggestions

Add the missing agents/*.md advisor files to the bundle (or remove the advisor references and inline the per-lens guidance) so the primary execution path resolves to real files.

Collapse the 'Preferred advisor orchestration', 'Workflow summary', and 'Advisors' sections into a single sequenced workflow plus a short file index to remove triplication.

Merge the redundant safety bullets (e.g. the reuse-research-packet and do-not-re-fetch-in-each-advisor pair) into one concrete instruction to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept padding, but the orchestration is described three times (Preferred advisor orchestration, Workflow summary, Advisors list) and several Always bullets restate the same idea (e.g. reuse-one-research-packet vs. do-not-re-fetch-in-each-advisor).

3 / 5

Actionability

References concrete templates and MCP calls, but the primary executable path delegates to seven agents/*.md advisor files that are not present in the bundle, leaving the core steps without their referenced detail.

3 / 5

Workflow Clarity

Clear numbered sequence (Workflow summary 1-6) with explicit validation gates — research checkpoint comment before mutation, final verdict comment before approval/merge — appropriate for a mutation-capable skill, though some gating detail lives in references/instructions.md rather than inline.

4 / 5

Progressive Disclosure

Good signaling via dedicated Assets/References/Advisors sections with one-line descriptions, but seven referenced agents/*.md paths do not resolve to actual bundle files, so navigation leads to dead ends.

3 / 5

Total

13

/

20

Passed

Description

100%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, third-person description that names concrete capabilities, supplies natural trigger phrases users would actually say, and draws explicit use/not-use boundaries. It is concise yet complete and distinct from neighboring skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template' — with comprehensive coverage of the review surface.

5 / 5

Completeness

Explicitly answers both 'what' (review dependency PRs with the listed capabilities) and 'when' via a USE FOR / DO NOT USE FOR block with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural triggers including quoted user phrases ('review this dependency PR', 'should we merge this update') plus tool synonyms (Renovate, Dependabot) and the dependency-update domain vocabulary.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (dependency PR review) and an explicit DO NOT USE FOR boundary (feature PRs, app code, bot config) keeps conflict risk minimal.

5 / 5

Total

20

/

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

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.