code-review
npx machina-cli add skill a5c-ai/babysitter/code-review --openclawCode Review
Overview
Assess code quality, design, correctness, and maintainability through a structured 9-step review workflow. Uses Conventional Comments format with file-specific references.
When to Use
- After implementation phase completes
- When reviewing code changes before merge
- As part of the /review-code command
Process
- Identify modified files via git
- Assess change magnitude for review depth
- Execute 9-step review: context, correctness, design, testing, security flags, operations, maintainability
- Synthesize findings in standardized report
- Deliver verdict with rationale
Review Depth Scaling
- Under 200 lines: full detail review
- 200-1000 lines: focused review on critical areas
- Over 1000 lines: architectural-level review only
Verdicts
- APPROVE: Ready for security review
- APPROVE WITH NITS: Non-blocking suggestions only
- REQUEST CHANGES: Blocking issues exist (user may override)
Key Rules
- Provide specific file paths and line numbers
- Include at least one positive comment per review
- Use Conventional Comments format with decorations
- Explain reasoning, not just observations
- Limit critical issues to top 5 per category
- Reviews are soft gates preserving user autonomy
Tool Use
Invoke via babysitter process: methodologies/rpikit/rpikit-review
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/rpikit/skills/code-review/SKILL.mdView on GitHub Overview
This skill performs a structured quality assessment of code, covering quality, design, correctness, and maintainability through a 9-step workflow. It uses the Conventional Comments format with file-specific references to make findings actionable.
How This Skill Works
It begins by identifying modified files, then assesses change magnitude to determine depth. It executes a 9-step review (context, correctness, design, testing, security flags, operations, maintainability), then synthesizes findings into a standardized report and delivers a rationale-based verdict.
When to Use It
- After implementation phase completes
- When reviewing code changes before merge
- As part of the /review-code command
- During PR reviews in CI pipelines to standardize comments
- When you need file-specific references and Conventional Comments format
Quick Start
- Step 1: Identify modified files via git
- Step 2: Assess change magnitude for review depth
- Step 3: Run the 9-step rpikit-review via babysitter: methodologies/rpikit/rpikit-review; synthesize the report and deliver a verdict with rationale
Best Practices
- Provide specific file paths and line numbers
- Include at least one positive comment per review
- Use Conventional Comments format with decorations
- Explain reasoning, not just observations
- Limit critical issues to top 5 per category
Example Use Cases
- Review a small PR under 200 lines with full detail using conventional comments and file-specific references.
- Review a patch of 200–1000 lines focusing on critical areas like correctness and security flags.
- Perform an architectural-level review for changes exceeding 1000 lines, prioritizing maintainability and design.
- Deliver an APPROVE WITH NITS where non-blocking suggestions improve code quality.
- Run a soft-gate review that preserves user autonomy while documenting rationale and next steps.
