code-reviewer

Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering-team/skills/code-reviewer/SKILL.md

Quality

Content

71%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-organized, concise, and actionable with runnable commands, threshold tables, and a clear multi-language dispatch model. The main weakness is progressive disclosure: the body references rules/universal.md, languages/*.md, and expected_outputs/ that are not present in the skill bundle, so navigation targets are partly missing.

Suggestions

Ensure referenced bundle paths (rules/universal.md, languages/*.md, expected_outputs/) actually ship with the skill, or note which are created on demand, so progressive-disclosure references resolve.

Add an explicit verification checkpoint (e.g., re-run with --json and diff against expected_outputs) into the standard review workflow so validation is shown as a feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable command blocks, dispatch table, and thresholds that earn their place; minor instances of slightly redundant phrasing (e.g., 'That is always exactly 2 additional files, regardless of scope').	4 / 5
Actionability	Provides concrete, runnable python commands with flags for all three tools plus a dispatch table and threshold tables; minor gaps such as expected_outputs/ fixtures being referenced without showing expected workflow for a brand-new reviewer.	4 / 5
Workflow Clarity	Clear loading-order sequence and a numbered 'Adding a New Language' procedure with deterministic-analyzer steps, plus a regression-diff verification step; minor checkpoint gaps around confirming scripts ran successfully before report generation.	4 / 5
Progressive Disclosure	Structure is good (dispatch table, tools sections) and references languages/*.md one level deep, but the referenced rules/ and languages/ directories and expected_outputs/ do not exist in the bundle, so the one-level-deep references are not actually backed by present files, capping organization.	3 / 5
	Total	15 / 20 Passed

Description

88%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, specific, and complete with an explicit 'Use when' clause and concrete actions across a clearly named domain. Minor room to add common synonyms like 'code review', 'code smells', and 'SOLID violations' as natural trigger terms.

Suggestions

Add natural synonyms users might say — e.g., 'code review', 'code smells', 'SOLID violations' — to broaden trigger-term coverage.

Consider trimming the long enumeration of 14 languages if it adds little trigger value; the language list is coverage detail rather than a trigger phrase.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports) with broad language coverage — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers what (code review automation across listed languages with the three actions) and when ('Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'reviewing pull requests', 'analyzing code quality', 'identifying issues', 'generating review checklists', but lacks some common synonyms/extensions (e.g., 'code smells', 'SOLID', 'code review') users might naturally say.	4 / 5
Distinctiveness Conflict Risk	A clear niche (PR review automation with multi-language support) with mostly distinct triggers, though the broad 'analyzing code quality' could overlap with general linter or refactoring skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering-team/skills/code-reviewer/SKILL.md
Commit: 19392f7

Reviewed: ~8 hours ago

Table of Contents

Discovery Implementation Validation

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.