Skill1.8k repo starsupdated 6d ago

code-review-orchestration

This Claude Code skill orchestrates six specialized review agents that evaluate code submissions across architecture, security, performance, testing, quality, and documentation dimensions simultaneously. Each agent independently scores its assigned area using weighted percentages, aggregating results into a final recommendation ranging from APPROVE to REJECT based on overall score thresholds and critical issue detection. Use this skill as a comprehensive code review gate before merging or during post-implementation quality checks.

View source Repository: babysitter

Install in Claude Code

Copy

git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/code-review-orchestration && cp -r /tmp/code-review-orchestration/library/methodologies/claudekit/skills/code-review-orchestration ~/.claude/skills/code-review-orchestration

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

## Scoring and Recommendation

- **APPROVE**: overall >= 80 AND zero critical issues
- **REQUEST_CHANGES**: overall >= 60 OR has critical issues
- **REJECT**: overall < 60

## When to Use

- `/code-review` slash command
- Post-implementation review in spec execution
- Pre-merge quality gate

## Agents Used

- `code-review-coordinator`, `security-analyst`, `performance-analyst`
- `testing-specialist`, `architecture-reviewer`

## Processes Used By

- `claudekit-code-review` (primary consumer)
- `claudekit-orchestrator` (via command dispatch)