CtrlK
BlogDocsLog inGet started
Tessl Logo

code-reviewer

Provides structured code review against plans and standards. Use when a feature is complete and needs validation, when reviewing code before merge, or when assessing quality and test coverage—e.g., "finished step X", "ready for review", "validate architecture", "check quality and tests".

89

1.71x
Quality

87%

Does it follow best practices?

Impact

89%

1.71x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

62%

User Management API Code Review

Structured review output and announcement protocol

Criteria
Without context
With context

Opening announcement

0%

100%

Overview section present

50%

100%

Findings section present

28%

100%

Tests/verification section present

25%

100%

Final statement present

0%

100%

Severity closing count

0%

100%

Severity labels on findings

25%

100%

Location field on findings

50%

100%

Rationale field on findings

50%

100%

Fix field on findings

75%

100%

Severity ordering

85%

100%

Plan alignment addressed

100%

100%

80%

21%

Analytics Dashboard Widget Review

Domain checklist use and architecture review

Criteria
Without context
With context

Strengths acknowledged

55%

77%

Architecture assessment present

70%

90%

Frontend-specific accessibility finding

100%

100%

Frontend-specific component design finding

100%

100%

Frontend performance concern raised

37%

0%

Documentation/standards check present

44%

77%

Rationale on every finding

77%

100%

Code examples in fixes

100%

100%

Overview is concise

100%

100%

Verification suggestions included

0%

100%

Final statement present

0%

100%

Opening announcement present

0%

0%

89%

28%

Order Management Database Layer Review

Plan alignment and finding format completeness

Criteria
Without context
With context

Plan alignment first

30%

70%

Deviation identified

100%

100%

Database transaction concern

100%

100%

Missing index finding

100%

100%

Migration reversibility finding

100%

100%

Fix with code example

100%

100%

All files reviewed

100%

100%

Severity labels used correctly

0%

100%

Rationale on every finding

100%

100%

Closing count statement

0%

100%

Final statement present

0%

100%

Opening announcement present

0%

0%

Repository
jjjermiah/dotagents
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.