CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-code-review-implementation

This skill should be used when the user says "review implementation", "review the project", "check implementation", "quality review", "validate implementation", "implementation review", or wants a post-execution quality gate to verify that the implementation follows the project's stored code and testing patterns and matches the plan. Reports issues as ERRORS, WARNINGS, INFO with a verdict. Do NOT use this for reviewing PRs (use arn-code-review-pr) or validating plans (use arn-code-review-plan).

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A well-structured, highly actionable review workflow with clear sequencing and concrete checklists. Its main weaknesses are repeated boilerplate across the pattern-compliance sections and several large conditional subsections that remain inline instead of being pushed to reference files.

Suggestions

Factor the repeated 'for each documented pattern: identify → read → check → generate findings' procedure out of the code/UI/testing/security sections into a single shared template, referencing it from each section.

Move the lengthy Step 3b (Visual Regression), 3c (Cross-Layer Comparison), and 3d (Sketch Promotion) detail into separate reference files under references/, keeping SKILL.md as an overview that links to them — this would also improve progressive disclosure.

Tighten the report template and verdict-logic prose; the severity/finding-code tables already carry the information, so surrounding narration can be trimmed.

DimensionReasoningScore

Conciseness

Mostly concrete but padded — the 'Read X. For each documented pattern: 1. Identify ... 2. Read ... 3. Check ... 4. Generate findings' structure is repeated nearly verbatim across the code, UI, testing, and security pattern sections, and could be factored into a shared procedure; not quite 'every token earns its place'.

2 / 3

Actionability

Provides executable checklists with CheckIDs, severities, specific finding codes (CP-[PatternName]-CONFLICT, VR-L[N]-...), exact file paths to read, and a copy-ready report template with verdict logic — concrete and copy-paste ready.

3 / 3

Workflow Clarity

A clearly sequenced five-step pipeline (Load → Plan Compliance → Pattern/Visual/Cross-layer/Sketch → Cross-Phase → Report) with explicit conditional skip rules and a dedicated Error Handling section mapping failure modes to recovery actions.

3 / 3

Progressive Disclosure

The one bundle file (references/cross-layer-comparison-guide.md) is correctly referenced one level deep in Step 3c, but the large visual-regression, cross-layer, and sketch-promotion subsections are kept entirely inline rather than split into references, so content that could be separate is inline.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, concrete, with explicit trigger phrases and a clear what/when pairing. The negative disambiguation against sibling review skills sharply lowers conflict risk.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'verify that the implementation follows the project's stored code and testing patterns and matches the plan' and 'Reports issues as ERRORS, WARNINGS, INFO with a verdict' — naming the domain and specific output classification rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('verify ... follows ... patterns and matches the plan ... Reports issues ... with a verdict') and when ('This skill should be used when the user says ... or wants a post-execution quality gate').

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say — 'review implementation', 'review the project', 'check implementation', 'quality review', 'validate implementation', 'implementation review' — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Has an explicit disambiguation clause — 'Do NOT use this for reviewing PRs (use arn-code-review-pr) or validating plans (use arn-code-review-plan)' — giving it a clear niche unlikely to trigger the wrong skill.

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.