code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

21%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 a skeletal, generic template: vague instructions, a padded role-restatement paragraph, an empty Capabilities section, and links to 11 bundle files that do not exist. It provides almost no executable guidance and fails its own progressive-disclosure structure.

Suggestions

Create the referenced `resources/implementation-playbook.md` and the 10 `sub-skills/*.md` files, or remove the dead links and inline the actual guidance.

Replace the vague instruction bullets and the buzzword-filled "Expert Purpose" paragraph with concrete, executable steps (specific commands/tools, a review checklist, validation commands).

Add a real sequenced review workflow with explicit validation checkpoints (e.g. run static analysis -> review findings -> verify fix) instead of the empty "## Capabilities" section.

Dimension	Reasoning	Score
Conciseness	The "Expert Purpose" paragraph ("Masters static analysis tools ... cutting-edge analysis tools and techniques") restates the description and pads with buzzwords Claude already knows, and the opening role sentence duplicates the frontmatter, making it noticeably verbose.	2 / 5
Actionability	Instructions are high-level hints ("Apply relevant best practices and validate outcomes", "Provide actionable steps and verification") with no concrete commands, code, or checklists, and the single concrete pointer targets a missing `resources/implementation-playbook.md`.	2 / 5
Workflow Clarity	The four instruction bullets are an unordered, vague list with no real sequence and no validation checkpoints, and the empty "## Capabilities" section offers no process to follow.	2 / 5
Progressive Disclosure	The body links to 11 referenced files (`resources/implementation-playbook.md` and 10 `./sub-skills/*.md`) none of which exist on disk, and the "## Capabilities" section is empty, making navigation to dead references impossible.	1 / 5
	Total	7 / 20 Passed

Description

55%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 states concrete capabilities clearly but relies on an instruction-style trigger ("Use PROACTIVELY") rather than natural user phrasings, capping completeness and trigger quality. It is reasonably specific but risks overlap with the built-in code-review skill.

Suggestions

Add a "Use when ..." clause with natural user triggers such as "review my pull request", "find bugs in this diff", or "check this code for security issues".

Drop the "Use PROACTIVELY" phrasing in favor of concrete trigger conditions a user would actually say.

Sharpen the niche (e.g. "AI-assisted deep code review of diffs") to reduce overlap with the built-in code-review skill.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ("static analysis tools, security scanning, and configuration review", "security vulnerabilities, performance optimization, and production reliability"), with only minor coverage gaps, matching the anchor listing several specific actions.	4 / 5
Completeness	The "what" is clearly stated, but "when" is only weakly implied by "Use PROACTIVELY for code quality assurance" rather than concrete trigger phrases, matching the anchor for a clear what with missing/weak when.	3 / 5
Trigger Term Quality	"code review", "security vulnerabilities", and "performance optimization" are somewhat natural, but "Use PROACTIVELY" is an instruction to Claude rather than a user-spoken trigger, and common phrasings like "review my PR" or "check this code" are missing.	3 / 5
Distinctiveness Conflict Risk	"code review expert" is a recognizable niche, but the description overlaps heavily with a built-in code-review skill and the "AI-powered analysis" framing is broad, so it could still trigger for related skills.	3 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 10 missing	Warning

	Total	13 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/code-reviewer/SKILL.md
Commit: c4a059b

Reviewed: 1 hour 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.