code-reviewer

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

1.54x

Quality

73%

Does it follow best practices?

Impact

99%

1.54x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

71%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 well-structured, actionable review workflow with concrete commands and a clear feedback structure. Its main weakness is mild verbosity from defining review pillars Claude already understands, and an implicit rather than explicit preflight retry loop.

Suggestions

Tighten the pillar definitions to checklist-style prompts (e.g. 'Correctness: bugs or logical errors?') instead of full explanatory sentences that restate what Claude already knows.

Add an explicit feedback loop after preflight: 'If preflight fails, surface the failures to the user, then re-run before proceeding with the review.'

Drop or shorten the opening 'This skill guides the agent...' sentence since the frontmatter description already conveys it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the pillar definitions re-explain concepts Claude already knows (e.g. 'Maintainability: Is the code clean, well-structured... Consider factors like code clarity, modularity...') and the opening sentence lightly pads, so it could be tightened.	3 / 5
Actionability	Provides concrete executable commands (gh pr checkout, npm run preflight, git status/diff) and a concrete feedback structure (Critical/Improvements/Nitpicks, Approved/Request Changes), with only minor gaps.	4 / 5
Workflow Clarity	A clear five-step sequence with a preflight validation checkpoint for remote PRs; falls short of 5 because there is no explicit validate→fix→retry feedback loop after preflight.	4 / 5
Progressive Disclosure	A self-contained, well-organized single file with clear section headers and no need for external references, matching the simple-skill exception for well-structured content.	5 / 5
	Total	16 / 20 Passed

Description

75%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.

A solid, specific description that clearly conveys scope and supported targets with natural trigger terms. It falls just short of top marks because the 'when to use' guidance is implicit rather than spelling out concrete user trigger phrases.

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and several concrete capabilities — 'local changes (staged or working tree) and remote Pull Requests (by ID or URL)' plus the focus areas — which matches 'lists several specific actions; minor gaps'.	4 / 5
Completeness	Clearly states what the skill does and gives a 'Use this skill to review code' trigger, but the 'when' lacks explicit concrete trigger phrases (e.g. 'when the user asks to review a PR'), so it is not a 5.	4 / 5
Trigger Term Quality	Includes natural terms a user would say — 'review code', 'local changes', 'Pull Requests' / 'PR' — giving good keyword coverage, though a few synonyms (e.g. 'diff', 'code audit') are missing.	4 / 5
Distinctiveness Conflict Risk	'Review code' with explicit local-vs-PR targeting is a mostly distinct niche with only minor overlap risk against other code-related skills.	4 / 5
	Total	16 / 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: google-gemini/gemini-cli
Path: .gemini/skills/code-reviewer/SKILL.md
Commit: 9a15c45

Reviewed: 1 day 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.