Skills for Real Engineers. Straight from my .agents directory.
code-review
Agent skill froma5c-ai/babysitter
Multi-dimensional code review across correctness, security, performance, maintainability, and test coverage.
How to install code-review
npx skills add a5c-ai/babysitter# or add only this skill to Claude Code: copy the folder
library/methodologies/bmad-method/skills/code-review/
# into
~/.claude/skills/code-review/ (all projects)
.claude/skills/code-review/ (one project)
1# Code Review23Multi-dimensional code review across correctness, security, performance, maintainability, and test coverage.45## Agents6- Amelia (Developer) - `bmad-dev-amelia` (full team mode)7- Barry (Solo Dev) - `bmad-solodev-barry` (quick flow mode)89## Workflow101. Review correctness: logic, edge cases, error handling112. Review security: validation, auth, data protection123. Review performance: efficiency, resources, caching134. Review maintainability: clarity, naming, SOLID145. Review test coverage: missing tests, quality156. Rate overall quality and identify tech debt167. Generate actionable recommendations1718## Inputs19- `projectName` - Project name20- `storyResults` - Implementation results to review2122## Outputs23- Overall rating and score (0-100)24- Category scores (5 dimensions)25- Finding list with severity and suggestions26- Technical debt identification27- Action items2829## Process Files30- `bmad-orchestrator.js` - Phase 4 code review31- `bmad-implementation.js` - Sprint code review32- `bmad-quick-flow.js` - Quick flow review
Excerpt shown under the repository's MIT license.
More skills in babysitter
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
