code-review
2
总安装量
2
周安装量
#66099
全站排名
安装命令
npx skills add https://github.com/kdcokenny/opencode-workspace --skill code-review
Agent 安装分布
amp
2
gemini-cli
2
github-copilot
2
codex
2
kimi-cli
2
cursor
2
Skill 文档
Code Review Philosophy
TL;DR
Systematic code review across 4 layers with severity classification. Only report findings with â¥80% confidence. Include file:line references for all issues.
When to Use This Skill
- Before reporting implementation completion
- When explicitly asked to review code
- When using the
/reviewcommand - As an independent audit after code changes
The 4 Review Layers
Layer 1: Correctness
- Logic errors and edge cases
- Error handling completeness
- Type safety and null checks
- Algorithm correctness
- Off-by-one errors
Layer 2: Security
- No hardcoded secrets or API keys
- Input validation and sanitization
- Injection vulnerability prevention (SQL, XSS, command)
- Authentication and authorization checks
- Sensitive data not logged
- OWASP Top 10 awareness
Layer 3: Performance
- No N+1 query patterns
- Appropriate caching strategies
- No unnecessary re-renders (React/frontend)
- Lazy loading where appropriate
- Memory leak prevention
- Algorithmic complexity concerns
Layer 4: Style & Maintainability
- Adherence to project conventions (check AGENTS.md)
- Code duplication (DRY violations)
- Complexity management (cyclomatic complexity)
- Documentation completeness
- Test coverage gaps
Severity Classification
| Severity | Icon | Criteria | Action Required |
|---|---|---|---|
| Critical | ð´ | Security vulnerabilities, crashes, data loss, corruption | Must fix before merge |
| Major | ð | Bugs, performance issues, missing error handling | Should fix |
| Minor | ð¡ | Code smells, maintainability issues, test gaps | Nice to fix |
| Nitpick | ð¢ | Style preferences, naming suggestions, documentation | Optional |
Confidence Threshold
Only report findings with â¥80% confidence.
If uncertain about an issue:
- State the uncertainty explicitly: “Potential issue (70% confidence): …”
- Suggest investigation rather than assert a problem
- Prefer false negatives over false positives (reduce noise)
Review Process
- Initial Scan – Identify all files in scope, understand the change
- Deep Analysis – Apply all 4 layers systematically to each file
- Context Evaluation – Consider surrounding code, project patterns, existing conventions
- Philosophy Check – Verify against code-philosophy (5 Laws) if applicable
- Synthesize Findings – Group by severity, deduplicate, prioritize
Output Format
Structure your review as:
- Files Reviewed – List all files analyzed
- Overall Assessment – APPROVE | REQUEST_CHANGES | NEEDS_DISCUSSION
- Summary – 2-3 sentence overview
- Critical Issues (ð´) – With file:line references
- Major Issues (ð ) – With file:line references
- Minor Issues (ð¡) – With file:line references
- Positive Observations (ð¢) – What’s done well (always include at least one)
- Philosophy Compliance – Checklist results if applicable
What NOT to Do
- Do NOT report low-confidence findings as definite issues
- Do NOT provide vague feedback without file:line references
- Do NOT skip any of the 4 layers
- Do NOT forget to note positive observations
- Do NOT modify any files during review
- Do NOT approve without completing the full review process
Adherence Checklist
Before completing a review, verify:
- All 4 layers analyzed (Correctness, Security, Performance, Style)
- Severity assigned to each finding
- Confidence â¥80% for all reported issues (or uncertainty stated)
- File names and line numbers included for all findings
- Positive observations noted
- Output follows the standard format