CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-review

Use when code changes need review before merge - validates architecture, types, security, and test coverage.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An efficient, highly actionable review workflow with real executable commands and a well-defined output taxonomy. The main improvements are small: fix the inconsistent $ARGUMENTS/$SCOPE variable and step numbering, and add brief guidance for handling failed checks.

Suggestions

Unify the scope variable: it is introduced as $ARGUMENTS in the Scope line but referenced as $SCOPE in step 2b; pick one name.

Rename the '2b' step to a proper sequential number so the 1-5 ordering is unambiguous.

Add one line on what to do when the automated checks fail (e.g., classify failures as VIOLATION/ATTENTION before proceeding), which would also sharpen the checklist item 'Naming: correct conventions' by pointing to where conventions are defined.

DimensionReasoningScore

Conciseness

The body is ~37 lean lines with zero concept explanations and telegraphic, high-density rules ("Services: no try/catch, no transformation, use $fetch"), fully assuming Claude's competence; every token earns its place, matching anchor 5 rather than anchor 4 which allows minor trims.

5 / 5

Actionability

Copy-paste-ready commands are given ("git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached ...", "nuxi typecheck", "npx eslint . --max-warnings 0") along with a concrete classification taxonomy and verdict options, matching anchor 4; it stops short of anchor 5 because items like "Naming: correct conventions" are vague and pattern details defer entirely to the external docs/ARCHITECTURE.md.

4 / 5

Workflow Clarity

A clear 1-5 sequence exists with explicit validation checkpoints (typecheck, eslint, vitest, automated pattern validation), matching anchor 4; it is below anchor 5 because there is no error-recovery guidance when checks fail, the numbering is inconsistent (a "2b" step), and the scope variable is defined as $ARGUMENTS but invoked as $SCOPE.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into clean sections with the compact pattern checklist inlined as core content, so the simple-skill exception applies for anchor 5; the external pointers (docs/ARCHITECTURE.md, /review-check-architecture) are clearly signaled and one level deep.

5 / 5

Total

18

/

20

Passed

Description

75%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 in third-person voice with an explicit 'Use when...' clause and a concrete enumeration of validation areas. Its main limitation is a single trigger scenario and missing common synonyms (PR, diff) that would sharpen both completeness and trigger matching.

DimensionReasoningScore

Specificity

"validates architecture, types, security, and test coverage" lists several concrete validation areas, matching anchor 4 (several specific actions, minor gaps); it is below anchor 5 because it never states what the skill produces (e.g., a report or verdict) and above anchor 3 because it covers four distinct areas rather than 1-2.

4 / 5

Completeness

Both parts are explicitly present: what ("validates architecture, types, security, and test coverage") and when ("Use when code changes need review before merge"), matching anchor 4; it is below anchor 5 because the when-clause covers a single scenario rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

"code changes", "review", and "before merge" are natural phrases users would say, giving good keyword coverage (anchor 4); it falls short of anchor 5 because common variations like "PR", "pull request", or "diff" are absent.

4 / 5

Distinctiveness Conflict Risk

Pre-merge code review with named validation domains (architecture, types, security, test coverage) carves a mostly distinct niche with only minor overlap risk against generic code-review skills, matching anchor 4; it is not anchor 5 because the trigger phrasing is broad enough to collide with a general review skill.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

packs/nuxt/skills/review-review/SKILL.md

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.