code-review-checklist

Code review guidelines covering code quality, security, and best practices.

Quality

50%

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 ./.agents/skills/code-review-checklist/SKILL.md

Quality

Content

50%

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

The skill is a well-organized, mostly lean code-review checklist with concrete named checks and a ready-to-use comment-severity guide, but it re-teaches some basic programming concepts and provides no sequenced workflow or progressive file structure. It sits solidly at the mid-level across all four dimensions.

Suggestions

Trim or collapse the Anti-Patterns section so it references rather than re-teaches basic concepts Claude already knows (magic numbers, deep nesting, early returns, 'any'), improving token efficiency.

Tighten abstract checklist items like 'Code does what it's supposed to do' into concrete, verifiable checks, or pair them with a brief 'how to verify' note.

Add a short sequenced review workflow (e.g. scan -> categorize findings by severity -> report) and consider splitting the anti-patterns/comments guides into referenced files for progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The checklist format is lean and assumes Claude's competence, but the Anti-Patterns section re-teaches basic concepts Claude already knows (magic numbers, deep nesting, early returns, the 'any' type), so it cannot reach the fully lean level 3.	2 / 3
Actionability	Many items name concrete things to check ('No SQL/NoSQL injection vulnerabilities', 'No N+1 queries') and the Review Comments Guide is copy-paste ready, but several items are abstract direction ('Code does what it's supposed to do', 'Clear naming') with no procedure for how to verify, so guidance is incomplete.	2 / 3
Workflow Clarity	Items are organized into clear categories (Correctness, Security, Performance, etc.), but there is no sequenced multi-step workflow or validation checkpoint for the review; the skill exceeds the <50-line simple-skill carve-out, so well-organized sections alone do not reach level 3.	2 / 3
Progressive Disclosure	The body is well-organized with clear ## / ### headers, but everything is inline in a single ~100-line file with no external references; content such as the anti-patterns and comments guides could be split out, and there is no one-level-deep reference structure to reach level 3.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 clearly states its domain and coverage areas in third person but stops short of listing concrete actions and omits an explicit 'Use when...' trigger clause, leaving it at the mid-level across all dimensions. It is distinguishable but broad enough to risk overlap with related skills.

Suggestions

Add concrete actions to the description, e.g. 'Flags SQL injection, hardcoded secrets, N+1 queries, and naming/abstraction issues during code review.'

Append an explicit trigger clause such as 'Use when reviewing a PR, checking code quality, or auditing security before merge.'

Narrow the scope wording to reduce overlap with generic linting/security skills, e.g. lead with 'Checklist-driven code review' to signal a distinct approach.

Dimension	Reasoning	Score
Specificity	Names the domain ('code review') and several concrete coverage areas ('code quality, security, and best practices'), but describes topics rather than listing concrete actions like flagging SQL injection or verifying tests, so it does not reach the multi-action level 3.	2 / 3
Completeness	It states what the skill does ('Code review guidelines covering...') but the description field itself lacks any 'Use when...' trigger clause, which per the rubric caps completeness at 2; not 1 because the 'what' is clearly stated.	2 / 3
Trigger Term Quality	'code review', 'code quality', and 'security' are natural terms a user would say, but the description omits common variations such as 'PR', 'pull request', or 'check my code', so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	'Code review' is a recognizable niche, but the broad scope ('code quality, security, and best practices') could overlap with general linting or security skills, so it is only somewhat distinct rather than clearly non-conflicting.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/code-review-checklist/SKILL.md
Commit: 04514f0

Reviewed: about 13 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.