Multi-Reviewer Patterns
Patterns for coordinating parallel code reviews across multiple quality dimensions, deduplicating findings, calibrating severity, and producing consolidated reports.
When to Use This Skill
- Organizing a multi-dimensional code review
- Deciding which review dimensions to assign
- Deduplicating findings from multiple reviewers
- Calibrating severity ratings consistently
- Producing a consolidated review report
Review Dimension Allocation
Available Dimensions
| Dimension |
Focus |
When to Include |
| Security |
Vulnerabilities, auth, input validation |
Always for code handling user input or auth |
| Performance |
Query efficiency, memory, caching |
When changing data access or hot paths |
| Architecture |
SOLID, coupling, patterns |
For structural changes or new modules |
| Testing |
Coverage, quality, edge cases |
When adding new functionality |
| Accessibility |
WCAG, ARIA, keyboard nav |
For UI/frontend changes |
Recommended Combinations
| Scenario |
Dimensions |
| API endpoint changes |
Security, Performance, Architecture |
| Frontend component |
Architecture, Testing, Accessibility |
| Database migration |
Performance, Architecture |
| Authentication changes |
Security, Testing |
| Full feature review |
Security, Performance, Architecture, Testing |
Finding Deduplication
When multiple reviewers report issues at the same location:
Merge Rules
- Same file:line, same issue — Merge into one finding, credit all reviewers
- Same file:line, different issues — Keep as separate findings
- Same issue, different locations — Keep separate but cross-reference
- Conflicting severity — Use the higher severity rating
- Conflicting recommendations — Include both with reviewer attribution
Deduplication Process
For each finding in all reviewer reports:
1. Check if another finding references the same file:line
2. If yes, check if they describe the same issue
3. If same issue: merge, keeping the more detailed description
4. If different issue: keep both, tag as "co-located"
5. Use highest severity among merged findings
Severity Calibration
Severity Criteria
| Severity |
Impact |
Likelihood |
Examples |
| Critical |
Data loss, security breach, complete failure |
Certain or very likely |
SQL injection, auth bypass, data corruption |
| High |
Significant functionality impact, degradation |
Likely |
Memory leak, missing validation, broken flow |
| Medium |
Partial impact, workaround exists |
Possible |
N+1 query, missing edge case, unclear error |
| Low |
Minimal impact, cosmetic |
Unlikely |
Style issue, minor optimization, naming |
Calibration Rules
- Security vulnerabilities exploitable by external users: always Critical or High
- Performance issues in hot paths: at least Medium
- Missing tests for critical paths: at least Medium
- Accessibility violations for core functionality: at least Medium
- Code style issues with no functional impact: Low
Consolidated Report Template
## Code Review Report
**Target**: {files/PR/directory}
**Reviewers**: {dimension-1}, {dimension-2}, {dimension-3}
**Date**: {date}
**Files Reviewed**: {count}
### Critical Findings ({count})
#### [CR-001] {Title}
**Location**: `{file}:{line}`
**Dimension**: {Security/Performance/etc.}
**Description**: {what was found}
**Impact**: {what could happen}
**Fix**: {recommended remediation}
### High Findings ({count})
...
### Medium Findings ({count})
...
### Low Findings ({count})
...
### Summary
| Dimension | Critical | High | Medium | Low | Total |
| ------------ | -------- | ----- | ------ | ----- | ------ |
| Security | 1 | 2 | 3 | 0 | 6 |
| Performance | 0 | 1 | 4 | 2 | 7 |
| Architecture | 0 | 0 | 2 | 3 | 5 |
| **Total** | **1** | **3** | **9** | **5** | **18** |
### Recommendation
{Overall assessment and prioritized action items}
Source: wshobson/agents → plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md
1---2name: multi-reviewer-patterns3description: "Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results."4category: ai-agents-and-harness5source_repo: wshobson/agents6source_path: "plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md"7source_url: https://github.com/wshobson/agents/blob/HEAD/plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md8---91011# Multi-Reviewer Patterns1213Patterns for coordinating parallel code reviews across multiple quality dimensions, deduplicating findings, calibrating severity, and producing consolidated reports.1415## When to Use This Skill1617- Organizing a multi-dimensional code review18- Deciding which review dimensions to assign19- Deduplicating findings from multiple reviewers20- Calibrating severity ratings consistently21- Producing a consolidated review report2223## Review Dimension Allocation2425### Available Dimensions2627| Dimension | Focus | When to Include |28| ----------------- | --------------------------------------- | ------------------------------------------- |29| **Security** | Vulnerabilities, auth, input validation | Always for code handling user input or auth |30| **Performance** | Query efficiency, memory, caching | When changing data access or hot paths |31| **Architecture** | SOLID, coupling, patterns | For structural changes or new modules |32| **Testing** | Coverage, quality, edge cases | When adding new functionality |33| **Accessibility** | WCAG, ARIA, keyboard nav | For UI/frontend changes |3435### Recommended Combinations3637| Scenario | Dimensions |38| ---------------------- | -------------------------------------------- |39| API endpoint changes | Security, Performance, Architecture |40| Frontend component | Architecture, Testing, Accessibility |41| Database migration | Performance, Architecture |42| Authentication changes | Security, Testing |43| Full feature review | Security, Performance, Architecture, Testing |4445## Finding Deduplication4647When multiple reviewers report issues at the same location:4849### Merge Rules50511. **Same file:line, same issue** — Merge into one finding, credit all reviewers522. **Same file:line, different issues** — Keep as separate findings533. **Same issue, different locations** — Keep separate but cross-reference544. **Conflicting severity** — Use the higher severity rating555. **Conflicting recommendations** — Include both with reviewer attribution5657### Deduplication Process5859```60For each finding in all reviewer reports:61 1. Check if another finding references the same file:line62 2. If yes, check if they describe the same issue63 3. If same issue: merge, keeping the more detailed description64 4. If different issue: keep both, tag as "co-located"65 5. Use highest severity among merged findings66```6768## Severity Calibration6970### Severity Criteria7172| Severity | Impact | Likelihood | Examples |73| ------------ | --------------------------------------------- | ---------------------- | -------------------------------------------- |74| **Critical** | Data loss, security breach, complete failure | Certain or very likely | SQL injection, auth bypass, data corruption |75| **High** | Significant functionality impact, degradation | Likely | Memory leak, missing validation, broken flow |76| **Medium** | Partial impact, workaround exists | Possible | N+1 query, missing edge case, unclear error |77| **Low** | Minimal impact, cosmetic | Unlikely | Style issue, minor optimization, naming |7879### Calibration Rules8081- Security vulnerabilities exploitable by external users: always Critical or High82- Performance issues in hot paths: at least Medium83- Missing tests for critical paths: at least Medium84- Accessibility violations for core functionality: at least Medium85- Code style issues with no functional impact: Low8687## Consolidated Report Template8889```markdown90## Code Review Report9192**Target**: {files/PR/directory}93**Reviewers**: {dimension-1}, {dimension-2}, {dimension-3}94**Date**: {date}95**Files Reviewed**: {count}9697### Critical Findings ({count})9899#### [CR-001] {Title}100101**Location**: `{file}:{line}`102**Dimension**: {Security/Performance/etc.}103**Description**: {what was found}104**Impact**: {what could happen}105**Fix**: {recommended remediation}106107### High Findings ({count})108109...110111### Medium Findings ({count})112113...114115### Low Findings ({count})116117...118119### Summary120121| Dimension | Critical | High | Medium | Low | Total |122| ------------ | -------- | ----- | ------ | ----- | ------ |123| Security | 1 | 2 | 3 | 0 | 6 |124| Performance | 0 | 1 | 4 | 2 | 7 |125| Architecture | 0 | 0 | 2 | 3 | 5 |126| **Total** | **1** | **3** | **9** | **5** | **18** |127128### Recommendation129130{Overall assessment and prioritized action items}131```132133---134135**Source:** [`wshobson/agents`](https://github.com/wshobson/agents) → `plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md`
wshobson