code-review-checklist

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

Quality

58%

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

68%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 lean, well-structured review checklist with concrete examples and a useful comment-severity guide. Its main weakness is the absence of an explicit review workflow order and a validation/verification checkpoint for the review process.

Suggestions

Add a short ordered workflow at the top (e.g. 1. read diff, 2. run through checklist by category, 3. summarize blocking vs. non-blocking findings) to give the review a clear sequence.

Add a verification checkpoint step (e.g. 'confirm each blocking issue has a file:line reference and a suggested fix before posting').

Consider splitting the AI/LLM patterns and anti-patterns into a reference file to keep SKILL.md closer to a quick-start overview.

Dimension	Reasoning	Score
Conciseness	The body is a terse checkbox checklist with compact ❌/✅ code snippets and no padding about concepts Claude already knows, fitting 'Efficient; minor instances of over-explanation that could be trimmed' (e.g. the inline emoji legend comments).	4 / 5
Actionability	Concrete checklists plus copy-pasteable TypeScript ❌/✅ examples and an emoji comment-format guide give mostly executable guidance with only minor gaps, matching the score-4 anchor.	4 / 5
Workflow Clarity	Categories (Correctness, Security, Performance, etc.) are listed but there is no explicit review sequence or validation/checkpoint step, and the checklist items are parallel rather than ordered, fitting 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The single ~104-line file is well-organized under clear section headers with no nested references and no bundle files to navigate, matching 'Good structure; most content is appropriately placed' (slightly over the 50-line simple-skill threshold so not a 5).	4 / 5
	Total	15 / 20 Passed

Description

48%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 clearly identifies the code-review niche and coverage areas but stays generic on actions and omits an explicit 'Use when' trigger clause (delegated to when_to_use). It is distinct but would benefit from concrete verbs and inline trigger phrases.

Suggestions

Add concrete verbs to the description, e.g. 'Flags correctness, security, performance, and quality issues in code during review'.

Append an explicit trigger clause to the description, e.g. 'Use when the user asks to review code, check a PR, or audit code quality'.

Include natural phrasings users say ('review my code', 'check this PR', 'code audit') directly in the description rather than only in when_to_use.

Dimension	Reasoning	Score
Specificity	The phrase 'Code review guidelines covering code quality, security, and best practices' names the domain and coverage areas but uses the generic verb 'covering' with no concrete actions (e.g. flag, check, comment), matching the score-2 anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	It gives a clear 'what' (code review guidelines across quality/security/best practices) but the description field itself has no 'Use when...' trigger clause, and the rubric caps completeness at 3 when explicit trigger guidance is missing from the description.	3 / 5
Trigger Term Quality	It includes relevant natural keywords ('code review', 'code quality', 'security', 'best practices') but misses common variations users actually say like 'review my code' or 'check this PR' (those live in when_to_use, not the description), so it fits 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	'Code review guidelines' carves a clear, distinct niche with minimal overlap against other skills, fitting 'Mostly distinct; minor overlap risk with closely related skills'.	4 / 5
	Total	12 / 20 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: 549ba3d

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.