install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/bmad-method/skills/code-review" ~/.claude/skills/a5c-ai-babysitter-code-review && rm -rf "$T"
manifest:
library/methodologies/bmad-method/skills/code-review/SKILL.mdsource content
Code Review
Multi-dimensional code review across correctness, security, performance, maintainability, and test coverage.
Agents
- Amelia (Developer) -
(full team mode)bmad-dev-amelia - Barry (Solo Dev) -
(quick flow mode)bmad-solodev-barry
Workflow
- Review correctness: logic, edge cases, error handling
- Review security: validation, auth, data protection
- Review performance: efficiency, resources, caching
- Review maintainability: clarity, naming, SOLID
- Review test coverage: missing tests, quality
- Rate overall quality and identify tech debt
- Generate actionable recommendations
Inputs
- Project nameprojectName
- Implementation results to reviewstoryResults
Outputs
- Overall rating and score (0-100)
- Category scores (5 dimensions)
- Finding list with severity and suggestions
- Technical debt identification
- Action items
Process Files
- Phase 4 code reviewbmad-orchestrator.js
- Sprint code reviewbmad-implementation.js
- Quick flow reviewbmad-quick-flow.js