lidge-jun/codexclaw / plugins/codexclaw/skills/dev-code-reviewer
cxc-dev-code-reviewer
VerifiedUse for code/PR/diff review and refactor audits. Triggers: review this, before merge, antipattern, 리뷰, 코드 리뷰, 머지 전에 확인.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.0 KB |
| agents/openai.yaml | config | 144 B |
| references/ai-assisted-review.md | markdown | 5.8 KB |
| references/common-antipatterns.md | markdown | 2.1 KB |
| references/external-review-evidence.md | markdown | 416 B |
| references/finding-verification.md | markdown | 1.9 KB |
| references/quality-thresholds.md | markdown | 1.2 KB |
| references/review-feedback.md | markdown | 2.0 KB |
| references/review-process.md | markdown | 2.8 KB |
| references/security-performance-review.md | markdown | 2.9 KB |
| references/subagent-and-slop-review.md | markdown | 3.3 KB |
| references/tech-debt.md | markdown | 5.1 KB |
references/review-process.md
View on GitHub## 1. Code Review Process
### Automated Pre-Scan
Run the smallest repo-native checks that observe the requested review scope.
Docs-only reviews use document/contract checks; a diagnostic review does not authorize
installs, product changes, or a repository-wide suite prohibited by the user.
1. Errors block review readiness.
2. Warnings are non-blocking but must be reported.
3. Tool findings appear before manual findings.
4. Unavailable tools are skipped with the gap stated; absence is non-blocking.
Routing: linters catch style, imports, and simple bugs; type checkers catch type
and null-safety errors; SAST catches common injection/auth patterns; dependency
audits catch known CVEs. Errors block, warnings inform. Manual review remains
responsible for architecture, correctness, business intent, and cross-file impact.
### Review Order (by impact, not preference)
1. **Architecture** — Does the approach make sense? Right layer? Right abstraction? Is this the right place for this code?
2. **Correctness** — Logic errors, edge cases, off-by-one, null/undefined handling, error paths
3. **Security** — Input validation, injection risks, auth checks, secrets exposure
4. **Performance** — N+1 queries, unbounded collections, missing indexes, unnecessary computation
5. **Maintainability** — Naming, structure, complexity, test coverage, documentation
6. **Style** — Last priority. Don't bikeshed formatting when there are real issues.
Delegation: coupling classification belongs to `dev-architecture` §3; boundary and
validation-location findings belong to `dev-architecture` §4.
### Review Mindset
- **Be specific.** "This could fail" → "This throws if `user` is null on line 42"
- **Suggest, don't demand.** Unless it's a security or correctness issue.
- **Explain why.** Not just "change X to Y" but "X causes N+1 queries because..."
- **Acknowledge good work.** If a complex problem is solved elegantly, say so briefly.
Compact finding example:
```yaml
severity: High
title: Missing ownership check permits cross-account access
location: src/routes/accounts.ts:42
trigger: Authenticated caller supplies another account ID
impact: Caller can read another user's account data
evidence: Handler loads by ID without constraining owner_id
remediation: Scope the query to the authenticated owner
verification: verified
```
### Pre-Review Checklist
- Build passes.
- Tests pass.
- The change explains what changed and why.
- The diff is small and structured enough to review.
- If the PR is one layer of a stack, follow `DEV-STACK-05` in `cxc-dev`
`stacked-prs.md` — review scope, standalone judgment, base-ref and
force-push checks, and the merge boundary all live there.
## Routing Role
Systematic code review patterns for finding real issues, not bikeshedding.
This skill activates by change-surface for review requests, pre-merge checks, or independent audit passes.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |