code-reviewer

Default code-quality route for broad code review, PR review, maintainability, correctness, and regression-risk checks. Do not use as the primary route for dedicated OWASP/security audits, review-feedback handling, completion verification, AI-code cleanup, or TDD/test-first work.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/code-reviewer/SKILL.md

Quality

Content

40%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 suffers from heavy boilerplate filler and a generic workflow that does not reflect an actual code-review process, though its reference structure and real script commands provide a usable skeleton.

Suggestions

Strip the generic 'Features' bullet lists, Tech Stack, and Common Commands sections — they are filler Claude already knows and add no review value.

Replace the generic 'Development Workflow' with an actual review workflow (read diff -> categorize findings by severity -> verify -> report) including validation checkpoints.

Give each script a concrete one-line description of what it checks and how to act on its output instead of phrases like 'Automated tool for pr analyzer tasks'.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with template filler ('Automated scaffolding', 'Best practices built-in', 'Deep analysis', 'Expert-level automation', 'Production-grade output') plus an irrelevant Tech Stack and generic Common Commands (npm/docker/kubectl) that earn no tokens.	2 / 5
Actionability	Real executable commands are provided (e.g., 'python scripts/code_quality_checker.py .'), but the per-script descriptions are vague ('Automated tool for pr analyzer tasks') and the actual review methodology — how to read a diff, categorize, and report findings — is missing.	3 / 5
Workflow Clarity	The 'Development Workflow' is a generic setup/run/apply sequence unrelated to code review, with no validation or feedback checkpoints; the rough steps are poorly defined for the skill's actual purpose.	2 / 5
Progressive Disclosure	References to real one-level-deep bundle files (code_review_checklist.md, coding_standards.md, common_antipatterns.md, python-style-guide.md, check_style.py) are clearly signaled and organized across 'Reference Documentation' and 'Resources' sections, with only minor filler that could be trimmed.	4 / 5
	Total	11 / 20 Passed

Description

70%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 specific and strongly distinguishes itself via an explicit negative-boundary list, but lacks an explicit 'Use when...' trigger clause, capping completeness at 3.

Suggestions

Add an explicit 'Use when the user asks for a fresh review of code or a PR...' trigger clause to lift completeness from 3 to 4-5.

Surface a couple of natural synonyms (e.g., 'code quality', 'code smell') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the code-review domain and several concrete review concerns ('PR review, maintainability, correctness, and regression-risk checks'), listing multiple specific actions with only minor coverage gaps.	4 / 5
Completeness	The 'what' is clearly stated but there is no explicit 'Use when...' trigger clause — 'when' is only weakly implied via 'Default code-quality route for...', which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural user-facing terms ('code review', 'PR review', 'maintainability', 'correctness', 'regression-risk') with good coverage, though a few synonyms ('code quality') are lightly represented.	4 / 5
Distinctiveness Conflict Risk	The explicit 'Do not use as the primary route for...' exclusion list (OWASP/security audits, review-feedback handling, completion verification, AI-code cleanup, TDD) carves out a clear niche with minimal conflict risk against sibling skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/code-reviewer/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.