Tooluck logoTooluck
SKILL.md

code-review-patterns

Agent skill froma5c-ai/babysitter

Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

How to install code-review-patterns

install code-review-patterns
# install the babysitter pack with the skills CLI
npx skills add a5c-ai/babysitter

# or add only this skill to Claude Code: copy the folder

library/methodologies/cc10x/skills/code-review-patterns/

# into

~/.claude/skills/code-review-patterns/ (all projects)

.claude/skills/code-review-patterns/ (one project)

library/methodologies/cc10x/skills/code-review-patterns/SKILL.md

MITFull file
1- Injection vulnerabilities (SQL, XSS, command)
2- Authentication and authorization patterns
3- Secrets handling (no hardcoded credentials)
4- Input validation and sanitization
5
6### Quality (weight: 25%)
7- Naming conventions and consistency
8- Code structure (SRP, cohesion, coupling)
9- Error handling completeness
10- Type safety (no `any` escapes)
11
12### Performance (weight: 20%)
13- Algorithmic complexity (flag O(n^2) or worse)
14- Resource and memory leaks
15- Database query efficiency (N+1)
16- Caching opportunities
17
18### Maintainability (weight: 25%)
19- Documentation (JSDoc/TSDoc for public APIs)
20- Test coverage adequacy
21- Readability (function length, nesting depth)
22- Tech debt markers (TODO, FIXME)
23
24## Confidence Gating
25
26- Only report issues with confidence >= 80%
27- Empty catch blocks are always critical (100% confidence)
28- Classify: critical, high, medium, low
29- Include actionable remediation for each issue
30
31## Router Contract
32
33Every review must produce: STATUS, BLOCKING, REQUIRES_REMEDIATION, issue counts.
34
35## When to Use
36
37- Code review step in BUILD workflow
38- Fix review in DEBUG workflow
39- Full REVIEW workflow
40
41## Agents Used
42
43- `code-reviewer` (primary consumer)
44- `silent-failure-hunter` (error handling dimension)

Excerpt shown under the repository's MIT license.

More skills in babysitter

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates