code-review

Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.

Install with Tessl CLI

npx tessl i github:secondsky/claude-skills --skill code-review

What are skills?

Review — 83%

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

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

90%

Respond to External Code Review

Code review reception

Criteria

Without context

With context

No performative agreement

100%

No gratitude expressions

100%

Stops for unclear item

100%

No partial implementation plan

YAGNI check on repository interface

53%

100%

Pushback on Comment 3

100%

Technical reasoning in pushback

100%

Accepts valid security comments

100%

No implementation before verification

100%

Blocking issues prioritized

100%

Without context: $0.2850 · 1m 30s · 11 turns · 12 in / 4,674 out tokens

With context: $0.3047 · 1m 10s · 13 turns · 14 in / 3,227 out tokens

87%

Fix and Verify a Cart Calculation Bug

Verification before completion claims

Criteria

Without context

With context

Ran bun test

Actual command shown

100%

Actual output included

100%

Test count stated

100%

No premature success claim

100%

No 'should/probably/seems' language

100%

Bug fix is correct

100%

Requirements checklist

70%

No unsupported claims

100%

Without context: $0.2368 · 43s · 12 turns · 13 in / 2,418 out tokens

With context: $0.4417 · 1m 25s · 21 turns · 21 in / 4,212 out tokens

70%

30%

Set Up Code Review After Feature Implementation

Code reviewer subagent dispatch

Criteria

Without context

With context

BASE_SHA via git

HEAD_SHA via git

Actual SHA values

100%

WHAT_WAS_IMPLEMENTED field

70%

100%

PLAN_OR_REQUIREMENTS field

70%

100%

DESCRIPTION field

80%

100%

Critical issues: fix immediately

30%

100%

Important issues: fix before proceeding

100%

Minor issues: noted for later

50%

100%

Task tool dispatch type

Without context: $0.7712 · 2m 49s · 31 turns · 32 in / 9,797 out tokens

With context: $0.7488 · 2m 20s · 32 turns · 33 in / 8,196 out tokens

Evaluated: 1 day ago
Agent: Claude Code

Table of Contents

Respond to External Code Review Fix and Verify a Cart Calculation Bug Set Up Code Review After Feature Implementation

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.