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.

Install with Tessl CLI

npx tessl i github:google-gemini/gemini-cli --skill code-reviewer

What are skills?

Review — 76%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 99%

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

36%

Code Review: User Search API Module

Review output structure and finding categorization

Criteria

Without context

With context

Summary section present

100%

Findings section present

25%

100%

Critical findings tier

100%

Improvements findings tier

100%

Nitpicks findings tier

37%

100%

Conclusion section present

25%

100%

Explicit recommendation

25%

100%

Security issue in Critical

100%

Why explanations provided

100%

Constructive language

100%

Without context: $0.2150 · 1m 8s · 8 turns · 9 in / 3,740 out tokens

With context: $0.3374 · 1m 55s · 14 turns · 13 in / 5,444 out tokens

97%

27%

Code Review: Inventory Report Service

Comprehensive analysis across all review pillars

Criteria

Without context

With context

Correctness addressed

83%

75%

Maintainability addressed

90%

100%

Readability addressed

100%

Efficiency addressed

100%

Security addressed

100%

Edge cases addressed

100%

Testability addressed

100%

Test suggestions specific

100%

All pillars in review

50%

100%

Without context: $0.2045 · 1m 21s · 6 turns · 7 in / 4,369 out tokens

With context: $0.3738 · 2m 1s · 13 turns · 13 in / 6,604 out tokens

100%

41%

Automate the PR Review Preparation Workflow

Remote PR review workflow and preparation steps

Criteria

Without context

With context

gh pr checkout used

100%

npm run preflight used

100%

Preflight before review

100%

PR context reading step

100%

Correct step ordering

41%

100%

Cleanup step included

71%

100%

PR number parameterized

100%

Without context: $0.2718 · 1m 10s · 12 turns · 12 in / 4,420 out tokens

With context: $0.3225 · 1m 5s · 17 turns · 892 in / 3,792 out tokens

Evaluated: about 10 hours ago
Agent: Claude Code

Table of Contents

Code Review: User Search API Module Code Review: Inventory Report Service Automate the PR Review Preparation Workflow

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.