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

52%

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

22%

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

The body reads as a generic templated toolkit rather than a focused code-review skill: it is verbose with off-topic content, offers only placeholder-level script guidance, and lacks any real sequenced review workflow with validation. Bundle references are real and shallow, which is the main structural strength.

Suggestions

Strip the unrelated Tech Stack, Common Commands, and generic Best Practices sections to reclaim tokens and remove content Claude already knows.

Replace placeholder script docs ('[options]', '[arguments]') with concrete flags and an example input/output so guidance is copy-paste ready.

Add an explicit sequenced review workflow (read diff -> classify issues by category -> prioritize -> report) with a verification/checklist checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic content Claude already knows — a universal Tech Stack (TypeScript/Swift/Kotlin/Flutter/AWS), unrelated Common Commands (npm run dev, docker-compose up, kubectl apply), and templated feature bullets ('Deep analysis', 'Production-grade output'); not score 2 because the verbosity is pervasive rather than occasional.	1 / 3
Actionability	Real script paths are given (e.g. 'python scripts/code_quality_checker.py <target-path> [--verbose]') but use vague placeholders like '[options]' and '[arguments]' with no concrete flags or example outputs; not score 3 because guidance is not copy-paste ready, and not score 1 because executable script invocations do exist.	2 / 3
Workflow Clarity	No sequenced code-review workflow with validation checkpoints; the 'Development Workflow' is generic setup->run->'apply fixes' with no review steps or verification; matches the unclear/missing-steps anchor rather than score 2's partial sequence.	1 / 3
Progressive Disclosure	Referenced bundle files (references/.md, scripts/.py) all exist and are signaled one level deep, but the body still inlines content that belongs in references (Tech Stack, Common Commands, generic Best Practices); not score 3 because of the inline bloat, and not score 1 because references are real and shallow.	2 / 3
	Total	6 / 12 Passed

Description

82%

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, specific description with excellent distinctiveness via explicit sibling-skill carve-outs and good trigger terms. Its main gap is the absence of a positive 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit positive trigger clause such as 'Use when the user asks to review code or a PR for correctness, maintainability, or regression risk' to raise completeness.

Lead with the 'what' before the negative carve-outs so the primary trigger is immediately visible.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review domains — 'code review, PR review, maintainability, correctness, and regression-risk checks' — matching the multi-action anchor; not score 2 because the coverage is comprehensive rather than partial.	3 / 3
Completeness	Clearly states what it does but lacks a positive 'Use when...' clause — the 'when' is only implied via scope plus negative carve-outs, so completeness is capped at 2 per the missing-trigger-guidance rule; not 3 because there is no explicit positive trigger.	2 / 3
Trigger Term Quality	Uses natural terms users say ('code review', 'PR review', 'maintainability', 'regression risk') with good coverage; not score 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	Explicit negative routing to sibling skills (security-reviewer, receiving-code-review, verification-before-completion, deslop, tdd-guide) gives a clear niche unlikely to conflict; not 2 because the carve-outs make it strongly distinguishable.	3 / 3
	Total	11 / 12 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: f627ab5

Reviewed: about 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.