PluginBench
Skill
Pass
Audit score 90

multi-reviewer-patterns

wshobson/agents

Coordinate parallel code reviews across multiple dimensions with deduplication, severity calibration, and consolidated reporting.

What is multi-reviewer-patterns?

Organize multi-dimensional code reviews by assigning reviewers to specific quality dimensions (Security, Performance, Architecture, Testing, Accessibility), then deduplicate findings, calibrate severity consistently, and produce a consolidated report. Use this when you need structured multi-reviewer coordination with consistent severity ratings and unified output.

  • Allocate code review dimensions (Security, Performance, Architecture, Testing, Accessibility) based on change type
  • Deduplicate findings from multiple reviewers using merge rules for same location and issue type
  • Calibrate severity ratings consistently across reviewers using defined criteria (Critical, High, Medium, Low)
  • Consolidate findings into a structured report organized by severity and dimension
  • Cross-reference conflicting recommendations and co-located issues with reviewer attribution

How to install multi-reviewer-patterns

npx skills add https://github.com/wshobson/agents --skill multi-reviewer-patterns
Claude Code
Cursor
Windsurf
Cline

How to use multi-reviewer-patterns

  1. 1.Select review dimensions based on the type of change (use the Recommended Combinations table)
  2. 2.Assign reviewers to each dimension and collect their findings
  3. 3.For each finding, identify duplicates using the Merge Rules (same file:line, same issue)
  4. 4.Merge duplicate findings, keeping the higher severity rating and more detailed description
  5. 5.Apply Severity Calibration Rules to ensure consistent ratings across all findings
  6. 6.Organize findings by severity level (Critical, High, Medium, Low)
  7. 7.Generate a consolidated report using the provided template with summary table by dimension

Use cases

Good for
  • Reviewing an API endpoint change across Security, Performance, and Architecture dimensions
  • Consolidating findings from multiple reviewers on a frontend component with different severity assessments
  • Deduplicating duplicate findings reported by both Security and Testing reviewers at the same code location
  • Producing a unified code review report with summary table for stakeholder communication
  • Calibrating severity ratings when reviewers disagree on impact level of the same issue
Who it's for
  • Code review coordinators managing multi-reviewer processes
  • Engineering leads organizing structured reviews for critical changes
  • Teams implementing consistent severity rating standards
  • Projects requiring consolidated reporting across multiple review dimensions

multi-reviewer-patterns FAQ

How do I decide which review dimensions to include?

Use the Recommended Combinations table based on your change type. For example, API endpoint changes should include Security, Performance, and Architecture. Always include Security for code handling user input or authentication.

What if two reviewers report the same issue at the same location?

Merge them into one finding, credit both reviewers, keep the more detailed description, and use the higher severity rating. Tag as merged and include both reviewer attributions.

How do I handle conflicting severity ratings for the same issue?

Always use the higher severity rating. If reviewers disagree on recommendations, include both with clear attribution to each reviewer.

What makes a finding Critical vs. High severity?

Critical findings cause data loss, security breaches, or complete failure (certain/very likely impact). High findings cause significant functionality degradation (likely impact). Security vulnerabilities exploitable by external users are always Critical or High.

Should I keep findings that appear in multiple locations?

Yes, keep them as separate findings but cross-reference them. Only merge findings at the exact same file:line that describe the same issue.

Full instructions (SKILL.md)

Source of truth, from wshobson/agents.


name: multi-reviewer-patterns description: 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. version: 1.0.2

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

DimensionFocusWhen to Include
SecurityVulnerabilities, auth, input validationAlways for code handling user input or auth
PerformanceQuery efficiency, memory, cachingWhen changing data access or hot paths
ArchitectureSOLID, coupling, patternsFor structural changes or new modules
TestingCoverage, quality, edge casesWhen adding new functionality
AccessibilityWCAG, ARIA, keyboard navFor UI/frontend changes

Recommended Combinations

ScenarioDimensions
API endpoint changesSecurity, Performance, Architecture
Frontend componentArchitecture, Testing, Accessibility
Database migrationPerformance, Architecture
Authentication changesSecurity, Testing
Full feature reviewSecurity, Performance, Architecture, Testing

Finding Deduplication

When multiple reviewers report issues at the same location:

Merge Rules

  1. Same file:line, same issue — Merge into one finding, credit all reviewers
  2. Same file:line, different issues — Keep as separate findings
  3. Same issue, different locations — Keep separate but cross-reference
  4. Conflicting severity — Use the higher severity rating
  5. 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

SeverityImpactLikelihoodExamples
CriticalData loss, security breach, complete failureCertain or very likelySQL injection, auth bypass, data corruption
HighSignificant functionality impact, degradationLikelyMemory leak, missing validation, broken flow
MediumPartial impact, workaround existsPossibleN+1 query, missing edge case, unclear error
LowMinimal impact, cosmeticUnlikelyStyle 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}