code-review-excellence

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Install with Tessl CLI

npx tessl i github:wshobson/agents --skill code-review-excellence

What are skills?

Review — 64%

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 — 86%

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

82%

17%

Code Review: User Authentication API Endpoint

Review format and severity labeling

Criteria

Without context

With context

Template: Summary section

100%

Template: Strengths section

100%

Template: Required Changes section

100%

Template: Suggestions section

100%

Template: Verdict section

62%

100%

Blocking label used

60%

100%

Nit/suggestion labels used

50%

100%

Praise label used

50%

100%

Question approach

Collaborative language

20%

40%

Identifies SQL injection

100%

Identifies weak hashing

100%

Without context: $0.2463 · 1m 32s · 8 turns · 57 in / 4,429 out tokens

With context: $0.6363 · 2m 25s · 26 turns · 25 in / 6,517 out tokens

86%

Code Review: React User Dashboard Components

TypeScript-specific bug detection

Criteria

Without context

With context

Flags 'any' in Props

100%

Flags 'any' in api-client

100%

Flags unhandled async errors

100%

Clear verdict

75%

100%

Flags prop mutation

100%

Does NOT flag formatting/style

100%

Question approach

Collaborative language

10%

80%

Flags test mutation issue

100%

Includes positive feedback

100%

Without context: $0.2452 · 1m 27s · 8 turns · 57 in / 4,344 out tokens

With context: $0.4360 · 2m 7s · 13 turns · 14 in / 6,289 out tokens

91%

23%

Code Review: Notification Service and Cart Logic

Python-specific bug detection

Criteria

Without context

With context

Flags mutable default: metadata

100%

Flags mutable default: channels

100%

Flags mutable default: preferences

100%

Flags mutable class attributes

100%

Flags broad exception catch

100%

Flags implementation-testing in tests

80%

100%

Does NOT flag formatting/style

100%

Question approach

50%

Collaborative language

20%

70%

Includes positive feedback

100%

Without context: $0.3414 · 1m 57s · 10 turns · 11 in / 5,962 out tokens

With context: $0.4924 · 2m 17s · 17 turns · 64 in / 6,948 out tokens

Evaluated: 3 days ago
Agent: Claude Code

Table of Contents

Code Review: User Authentication API Endpoint Code Review: React User Dashboard Components Code Review: Notification Service and Cart Logic

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.