code-reviewer

Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.

Install with Tessl CLI

npx tessl i github:jeffallan/claude-skills --skill code-reviewer

What are skills?

Review — 61%

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 — 96%

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Code Review: User Post Feed Service

Code review report structure and feedback quality

Criteria

Without context

With context

Summary section

100%

Critical issues section

100%

Major issues section

100%

Minor issues section

100%

Positive feedback section

100%

Questions for author

100%

Verdict included

100%

Severity labels

100%

File:line references

100%

Code examples in feedback

100%

Security issue identified

100%

N+1 query identified

100%

Magic numbers flagged

50%

100%

Without context: $0.2891 · 1m 40s · 11 turns · 11 in / 5,157 out tokens

With context: $0.3609 · 1m 51s · 15 turns · 11 in / 5,781 out tokens

92%

27%

User Search API: Implementation Review

Spec compliance two-stage review

Criteria

Without context

With context

Stage 1 before Stage 2

75%

91%

Missing requirements found

100%

Unnecessary addition flagged

100%

Interpretation gap identified

50%

90%

Professional skepticism

100%

Findings categorized

60%

90%

File:line references

100%

Spec compliance verdict

91%

100%

Code quality stage present

58%

Without context: $0.1587 · 57s · 6 turns · 55 in / 3,041 out tokens

With context: $0.4227 · 2m 11s · 17 turns · 64 in / 5,570 out tokens

98%

-2%

Respond to Code Review Feedback

Responding to review feedback professionally

Criteria

Without context

With context

No agreement theater

100%

All items addressed

100%

Specific fix acknowledgment

100%

Technical pushback format

100%

Restatement or clarification

100%

75%

No vague pushback

100%

Code or evidence cited

100%

Verification claimed correctly

100%

Output file present

100%

Without context: $0.1944 · 1m 7s · 8 turns · 8 in / 2,973 out tokens

With context: $0.2882 · 1m 9s · 14 turns · 13 in / 3,198 out tokens

Evaluated: about 7 hours ago
Agent: Claude Code

Table of Contents

Code Review: User Post Feed Service User Search API: Implementation Review Respond to Code Review Feedback

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.