Perform code review with quality scoring and configurable threshold enforcement.
Scanned 5/29/2026
Install to Claude Code
npx -y skills add a5c-ai/babysitter --skill code-review-gate --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Review Gate?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-code-review-gate)More formats (shields.io, HTML) on the badges page.
# Code Review Gate
Perform code review with quality scoring and configurable threshold enforcement.
## Agent
Code Reviewer - `automaker-code-reviewer`
## Workflow
1. Review all changed files for correctness
2. Check for security vulnerabilities
3. Identify performance issues
4. Verify test coverage adequacy
5. Check code style consistency
6. Detect dead code and debug artifacts
7. Verify no secrets in code
8. Assign quality score (0-100)
9. Make approve/reject decision
10. Enforce quality threshold gate
## Inputs
- `projectName` - Project name
- `featureId` - Feature identifier
- `branch` - Feature branch name
- `changedFiles` - Files to review
- `reviewPolicy` - Policy: 'auto', 'manual', 'hybrid'
- `qualityThreshold` - Minimum score (0-100)
## Outputs
- Review with approval, score, comments, security issues, quality gate pass/fail
## Process Files
- `automaker-orchestrator.js` - Phase 4
- `automaker-review-ship.js` - Stages 1-2
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...