code-reviewer

Elite code review expert specializing in modern AI-powered code

1.12x

Quality

26%

Does it follow best practices?

Impact

96%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/code-reviewer/SKILL.md

The canonical home for this skill is code-reviewer in sickn33/agentic-awesome-skills

Quality

Content

17%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 an extensive persona/capability catalogue with no executable guidance, no concrete commands, and a broken reference file. It tells Claude what the reviewer knows rather than what to do, making it largely non-actionable.

Suggestions

Cut the Capabilities, Behavioral Traits, and Knowledge Base lists down to a few lines and replace them with concrete review procedures (e.g. run specific lint/SAST commands, read the diff, report findings by severity).

Provide executable examples such as sample review comments, severity rubrics, or commands for running Semgrep/Snyk so guidance is copy-paste ready.

Fix or remove the missing `resources/implementation-playbook.md` reference, and move detailed checklists into real one-level-deep reference files with clear links.

Dimension	Reasoning	Score
Conciseness	The 160-line body is padded with capability lists, behavioral traits, and a knowledge base enumerating tools and concepts (SonarQube, OWASP Top 10, Clean Code, SOLID) that Claude already knows. It is noticeably verbose with many padded sections, though it stops short of tutorial-style concept explanation, keeping it above 1.	2 / 5
Actionability	There is no executable code, no concrete commands, and no specific procedures; the Instructions are generic ('Apply relevant best practices and validate outcomes') and the body only describes rather than instructs, matching the 'entirely vague or abstract' anchor.	1 / 5
Workflow Clarity	The 10-step 'Response Approach' gives a rough sequence but every step is abstract ('Analyze code context', 'Apply automated tools') with no concrete commands and no validation checkpoints, fitting the 'rough sequence with many gaps and validation absent' anchor.	2 / 5
Progressive Disclosure	The skill is a monolithic file inlining large capability/knowledge lists that belong in separate references, and its single reference (`resources/implementation-playbook.md`) does not exist in the bundle, so structure is minimal and the reference is broken.	2 / 5
	Total	7 / 20 Passed

Description

36%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 a brief role statement that names the code-review domain but lacks concrete capabilities and any explicit 'when to use' guidance. It reads more like a persona tagline than a trigger-rich skill description.

Suggestions

Replace the persona tagline with concrete actions, e.g. 'Reviews diffs for bugs, security, and performance issues; suggests fixes with code examples.'

Add an explicit trigger clause such as 'Use when reviewing a diff, pull request, or code change for correctness, security, or quality.'

Include natural synonyms users say ('review my code', 'check this PR', 'find bugs in this change') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code review') but offers no concrete actions, only the vague role claim 'Elite code review expert specializing in modern AI-powered code'. It does not reach 3 because no specific actions are listed, and stays above 1 because the domain is at least named.	2 / 5
Completeness	It provides a vague 'what' ('expert specializing in modern AI-powered code') with no 'Use when...' trigger guidance, so per the rubric a missing explicit trigger clause caps completeness and the vague what places it at 2 rather than 3.	2 / 5
Trigger Term Quality	'code review' is a natural keyword users would actually say, but the description lacks common variations or synonyms (e.g. 'review my code', 'check this PR', 'find bugs'). It fits the 'some relevant keywords but missing variations' anchor rather than 2 (which requires only generic language) or 4 (which needs broader natural-term coverage).	3 / 5
Distinctiveness Conflict Risk	'code review' is a recognizable niche, but the broad phrasing ('expert specializing in modern AI-powered code') overlaps with general code-assistance skills and the built-in /code-review skill, so it is somewhat specific yet still carries overlap risk.	3 / 5
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/code-reviewer/SKILL.md
Commit: 57c135b

Reviewed: 2 days 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.