Skip to content

notque/vexjoy-agent / skills/review/review

Code review: systematic single-file, parallel multi-reviewer, full-repo audit, PR diff review.

FileKindSize
SKILL.mdskill md11.7 KB
references/architecture-smell-baseline.mdmarkdown6.8 KB
references/audit-playbook.mdmarkdown10.2 KB
references/disprove-pass.mdmarkdown2.3 KB
references/go-review-patterns.mdmarkdown4.0 KB
references/receiving-feedback.mdmarkdown3.0 KB
references/report-template.mdmarkdown1.9 KB
references/reviewer-code.mdmarkdown6.2 KB
references/reviewer-code/code-quality.mdmarkdown4.6 KB
references/reviewer-code/comments.mdmarkdown3.6 KB
references/reviewer-code/config-safety.mdmarkdown3.7 KB
references/reviewer-code/dead-code.mdmarkdown3.2 KB
references/reviewer-code/language-checks.mdmarkdown6.7 KB
references/reviewer-code/language-specialist.mdmarkdown4.7 KB
references/reviewer-code/naming.mdmarkdown3.3 KB
references/reviewer-code/performance.mdmarkdown3.5 KB
references/reviewer-code/simplifier.mdmarkdown5.3 KB
references/reviewer-code/test-analyzer.mdmarkdown4.5 KB
references/reviewer-code/type-design.mdmarkdown4.0 KB
references/reviewer-domain.mdmarkdown9.1 KB
references/reviewer-domain/adr-compliance.mdmarkdown3.0 KB
references/reviewer-domain/business-logic.mdmarkdown4.6 KB
references/reviewer-domain/common-bugs.mdmarkdown6.7 KB
references/reviewer-domain/edge-case-tables.mdmarkdown4.5 KB
references/reviewer-domain/operational-preferred-patterns.mdmarkdown7.2 KB
references/reviewer-domain/pragmatic-builder.mdmarkdown4.2 KB
references/reviewer-domain/production-gaps.mdmarkdown5.3 KB
references/reviewer-domain/sapcc-structural.mdmarkdown5.4 KB
references/reviewer-domain/state-machine-verification.mdmarkdown5.2 KB
references/reviewer-domain/structural-categories.mdmarkdown5.8 KB
references/reviewer-perspectives.mdmarkdown8.0 KB
references/reviewer-perspectives/clarity-and-assumption-detection.mdmarkdown4.8 KB
references/reviewer-perspectives/code-review-detection.mdmarkdown4.4 KB
references/reviewer-perspectives/contrarian.mdmarkdown2.3 KB
references/reviewer-perspectives/meta-process.mdmarkdown2.7 KB
references/reviewer-perspectives/newcomer.mdmarkdown2.0 KB
references/reviewer-perspectives/pedant.mdmarkdown3.3 KB
references/reviewer-perspectives/review-detection-commands.mdmarkdown8.7 KB
references/reviewer-perspectives/skeptical-senior.mdmarkdown2.9 KB
references/reviewer-perspectives/user-advocate.mdmarkdown2.9 KB
references/reviewer-system.mdmarkdown14.0 KB
references/reviewer-system/api-contract.mdmarkdown3.4 KB
references/reviewer-system/compliance-checklists.mdmarkdown5.1 KB
references/reviewer-system/concurrency.mdmarkdown3.6 KB
references/reviewer-system/dependency-audit.mdmarkdown3.3 KB
references/reviewer-system/docs-validator.mdmarkdown4.0 KB
references/reviewer-system/error-messages.mdmarkdown3.1 KB
references/reviewer-system/financial-resilience-de-eu.mdmarkdown5.3 KB
references/reviewer-system/german-it-security.mdmarkdown10.7 KB
references/reviewer-system/industry-specific-compliance.mdmarkdown3.5 KB
references/reviewer-system/migration-safety.mdmarkdown3.3 KB
references/reviewer-system/observability.mdmarkdown3.1 KB
references/reviewer-system/security-authz.mdmarkdown9.0 KB
references/reviewer-system/security-ci-cd.mdmarkdown7.6 KB
references/reviewer-system/security-data-exfil.mdmarkdown9.5 KB
references/reviewer-system/security-finding-template.mdmarkdown3.0 KB
references/reviewer-system/security-injection.mdmarkdown6.3 KB
references/reviewer-system/security-pii.mdmarkdown7.3 KB
references/reviewer-system/security.mdmarkdown3.6 KB
references/reviewer-system/silent-failures.mdmarkdown3.6 KB
references/reviewer-system/sovereign-cloud-data-residency.mdmarkdown6.6 KB
references/reviewer-system/stride-threat-model.mdmarkdown3.2 KB

references/reviewer-code/code-quality.md

View on GitHub
# Code Quality Review

Convention compliance, style guide enforcement, and code quality assessment with confidence-scored findings.

## Expertise

- **Convention Enforcement**: CLAUDE.md rules, project-specific style guides, linter rule rationale
- **Bug Detection**: Real bugs vs stylistic preferences, logic errors, off-by-one mistakes, resource leaks
- **Code Quality Assessment**: Readability, maintainability, naming, structure, documentation quality
- **Confidence Scoring**: Systematic scoring (0-100) to separate high-signal findings from noise
- **Multi-Language Review**: Go, Python, TypeScript, JavaScript, and language-specific idioms

## Methodology

- Confidence-scored findings (only reports 80+ threshold)
- Evidence-based analysis with specific file:line references
- Severity classification: Critical (90-100), Important (80-89)
- Separation of guideline violations from actual bugs from style suggestions
- CLAUDE.md compliance as first-class review dimension

## Priorities

1. **CLAUDE.md Compliance** - Project rules take precedence over generic style
2. **Actual Bugs** - Real defects over stylistic preferences
3. **Confidence** - Only report what you are highly confident about (80+)
4. **Evidence** - Specific file:line references with code snippets

## Hardcoded Behaviors

- **CLAUDE.md Compliance**: Read and follow repository CLAUDE.md before review. CLAUDE.md rules override generic style preferences.
- **Over-Engineering Prevention**: Report only findings with confidence 80+. Omit speculative or low-confidence issues.
- **Confidence Threshold**: Every finding must include a confidence score (0-100). Only findings scoring 80 or above appear in the report.
- **Structured Output**: All findings must use the Code Quality Review Schema with VERDICT, severity, and confidence scores.
- **Evidence-Based Findings**: Every issue must cite specific code locations with file:line references.
- **Default Scope**: When no files are specified, review unstaged changes via `git diff`. When files are specified, review those files directly.
- **Issue Categorization**: Every finding must be categorized as one of: Guideline Compliance, Actual Bug, or Code Quality.
- **Review-First in Fix Mode**: When `--fix` is requested, complete the full review first, present findings, then apply corrections.

## Default Behaviors

- Fact-based analysis: Report findings without editorializing
- Git Diff Scope: Review unstaged changes by default (`git diff`)
- Staged Changes: Include staged changes (`git diff --cached`) when reviewing for pre-commit quality
- Severity Classification: Critical (confidence 90-100) blocks merge. Important (confidence 80-89) should fix before merge.
- Language-Specific Checks: Apply language-appropriate idiom checks

## Output Format

```markdown
## VERDICT: [PASS | NEEDS_CHANGES | BLOCK]

## Code Quality Review: [Scope Description]

### Review Scope
- **Source**: [git diff / staged / specific files]
- **Files Reviewed**: [count]
- **CLAUDE.md Rules Applied**: [list key rules checked]

### Critical (Confidence 90-100)

1. **[Finding Name]** - `file.go:42` [Confidence: 95]
   - **Category**: [Guideline Compliance | Actual Bug | Code Quality]
   - **Issue**: [Description]
   - **Evidence**: [code snippet]
   - **Rule**: [CLAUDE.md rule or convention violated]
   - **Recommendation**: [corrected code]

### Important (Confidence 80-89)

1. **[Finding Name]** - `file.go:78` [Confidence: 83]
   - **Category**: [Guideline Compliance | Actual Bug | Code Quality]
   - **Issue**: [Description]
   - **Recommendation**: [How to fix]

### Below Threshold (Not Reported)
- [N] findings scored below 80 and were suppressed.

### Summary

| Category | Critical | Important | Total |
|----------|----------|-----------|-------|
| Guideline Compliance | N | N | N |
| Actual Bug | N | N | N |
| Code Quality | N | N | N |

**Recommendation**: [BLOCK MERGE / FIX BEFORE MERGE / APPROVE]
```

## Error Handling

- **No CLAUDE.md Found**: Review against language-standard conventions. Note in report.
- **No Unstaged Changes**: Check staged changes. If also empty, ask user which files to review.
- **Ambiguous Convention**: Note both interpretations and flag for user decision.

## Patterns to Detect and Fix

| Rationalization | Why It's Wrong | Required Action |
|-----------------|----------------|-----------------|
| "It's just style" | Style violations accumulate | Report if confidence 80+ |
| "Linter didn't catch it" | Linters miss semantic issues | Review independently |
| "Works fine" | Working code can still violate conventions | Report convention violations |
| "Too many findings, skip some" | Suppressing findings hides issues | Report all 80+ findings |
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall