code-review-checklist

Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability

Quality

55%

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 ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/code-review-checklist/SKILL.md

Quality

Content

56%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 well-structured and offers genuinely actionable templates and code examples, but it is markedly verbose with heavily overlapping checklist sections and explains review fundamentals Claude already knows. It also keeps all content inline rather than splitting detailed checklists into reference files.

Suggestions

Collapse the redundant 'How It Works', 'Examples', and 'Complete Review Checklist' sections into one canonical checklist to remove repeated material and cut tokens.

Delete explanations of concepts Claude already knows (e.g. defining DRY, generic 'is the code readable?' prompts) and keep only skill-specific guidance.

Move the large example checklists and comment templates into separate reference files under references/ and link to them from SKILL.md so the main file stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~440-line body repeats the same checklist material across 'How It Works', 'Examples', and 'Complete Review Checklist', and litters generic questions Claude already knows ('Are inputs validated?', 'Is the code readable?') plus spelled-out basics like 'DRY principle (Don't Repeat Yourself)', fitting the anchor for noticeably verbose with several padded sections.	2 / 5
Actionability	It provides copy-paste-ready review comment templates and concrete bad/good JavaScript examples for validation, SQL injection, naming, and separation of concerns, with only minor gaps in the more interrogative 'How It Works' steps.	4 / 5
Workflow Clarity	Steps 1-6 (Context, Functionality, Code Quality, Security, Performance, Tests) are clearly sequenced and accompanied by a consolidated checklist; this is a read-only review skill so the destructive-operation validation cap does not apply, leaving only minor checkpoint gaps.	4 / 5
Progressive Disclosure	The file has clear section headers but is a single monolithic document with no bundle files (references/scripts/assets absent) and inlines large example/checklist blocks that could live in separate reference files, matching the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	13 / 20 Passed

Description

53%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 states what the skill covers but lacks any explicit 'when to use' trigger guidance and misses common trigger phrases like 'pull request' or 'PR'. It is reasonably distinct from other skills but only moderately specific in its actions.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when reviewing pull requests, conducting code audits, or establishing team review standards.'

Include natural trigger terms users actually say ('pull request', 'PR', 'code review', 'code audit') to improve trigger_term_quality.

Replace the single generic action 'conducting thorough code reviews' with multiple concrete verbs (e.g. 'walk through changed code, verify edge cases, flag security risks, and check test coverage').

Dimension	Reasoning	Score
Specificity	The description names the domain ('conducting thorough code reviews') and enumerates coverage areas ('functionality, security, performance, and maintainability'), but offers only one generic action ('conducting... reviews' via a 'checklist') rather than multiple concrete verbs, matching the anchor that lists 1-2 concrete actions.	3 / 5
Completeness	It gives a clear 'what' but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	It includes the natural term 'code reviews' but omits common variations a user would actually say such as 'pull request', 'PR', or 'code audit', fitting the anchor for some relevant keywords missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	'Checklist for conducting thorough code reviews' carves a mostly distinct niche with only minor overlap risk against closely related review skills, matching the 'mostly distinct' anchor.	4 / 5
	Total	13 / 20 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: duclm1x1/Dive-Ai
Path: docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/code-review-checklist/SKILL.md
Commit: 20ba150

Reviewed: 5 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.