Skills · Data & AI

Multi Reviewer Patterns

Unverified31/40

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.

Originally by wshobson · MIT

Claude CodePartialHas SKILL.md but declares no allowed-tools — Claude Code will ask for permission each time
CursorPartialPlain prose you can paste in — but no Cursor rules file
CodexPartialPlain prose you can paste in — but no AGENTS.md
Gemini CLIPartialPlain prose you can paste in
CopilotPartialPlain prose you can paste in — but no Copilot instructions file
npx agentalley add multi-reviewer-patterns

This command does not work yet — the CLI is still being built. Until then, use Raw in the reader below to take the file.

Who is stuck, and on what

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.

The whole source

No sign-in, no blur, nothing truncated
multi-reviewer-patterns/SKILL.md128 lines5.1 KBRawView on GitHub
Frontmatter — 3 properties
namemulti-reviewer-patterns
descriptionCoordinate 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.
version1.0.2
1---
2name: multi-reviewer-patterns
3description: 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.
4version: 1.0.2
5---A5No allowed-tools declared — no way to tell what this skill may touch
6 
7# Multi-Reviewer Patterns
8 
9Patterns for coordinating parallel code reviews across multiple quality dimensions, deduplicating findings, calibrating severity, and producing consolidated reports.
10 
11## When to Use This Skill
12 
13- Organizing a multi-dimensional code review
14- Deciding which review dimensions to assign
15- Deduplicating findings from multiple reviewers
16- Calibrating severity ratings consistently
17- Producing a consolidated review report
18 
19## Review Dimension Allocation
20 
21### Available Dimensions
22 
23| Dimension | Focus | When to Include |
24| ----------------- | --------------------------------------- | ------------------------------------------- |
25| **Security** | Vulnerabilities, auth, input validation | Always for code handling user input or auth |
26| **Performance** | Query efficiency, memory, caching | When changing data access or hot paths |
27| **Architecture** | SOLID, coupling, patterns | For structural changes or new modules |
28| **Testing** | Coverage, quality, edge cases | When adding new functionality |
29| **Accessibility** | WCAG, ARIA, keyboard nav | For UI/frontend changes |
30 
31### Recommended Combinations
32 
33| Scenario | Dimensions |
34| ---------------------- | -------------------------------------------- |
35| API endpoint changes | Security, Performance, Architecture |
36| Frontend component | Architecture, Testing, Accessibility |
37| Database migration | Performance, Architecture |
38| Authentication changes | Security, Testing |
39| Full feature review | Security, Performance, Architecture, Testing |
40 
41## Finding Deduplication
42 
43When multiple reviewers report issues at the same location:
44 
45### Merge Rules
46 
471. **Same file:line, same issue** — Merge into one finding, credit all reviewers
482. **Same file:line, different issues** — Keep as separate findings
493. **Same issue, different locations** — Keep separate but cross-reference
504. **Conflicting severity** — Use the higher severity rating
515. **Conflicting recommendations** — Include both with reviewer attribution
52 
53### Deduplication Process
54 
55```
56For each finding in all reviewer reports:
57 1. Check if another finding references the same file:line
58 2. If yes, check if they describe the same issue
59 3. If same issue: merge, keeping the more detailed description
60 4. If different issue: keep both, tag as "co-located"
61 5. Use highest severity among merged findings
62```
63 
64## Severity Calibration
65 
66### Severity Criteria
67 
68| Severity | Impact | Likelihood | Examples |
69| ------------ | --------------------------------------------- | ---------------------- | -------------------------------------------- |
70| **Critical** | Data loss, security breach, complete failure | Certain or very likely | SQL injection, auth bypass, data corruption |
71| **High** | Significant functionality impact, degradation | Likely | Memory leak, missing validation, broken flow |
72| **Medium** | Partial impact, workaround exists | Possible | N+1 query, missing edge case, unclear error |
73| **Low** | Minimal impact, cosmetic | Unlikely | Style issue, minor optimization, naming |
74 
75### Calibration Rules
76 
77- Security vulnerabilities exploitable by external users: always Critical or High
78- Performance issues in hot paths: at least Medium
79- Missing tests for critical paths: at least Medium
80- Accessibility violations for core functionality: at least Medium
81- Code style issues with no functional impact: Low
82 
83## Consolidated Report Template
84 
85```markdown
86## Code Review Report
87 
88**Target**: {files/PR/directory}
89**Reviewers**: {dimension-1}, {dimension-2}, {dimension-3}
90**Date**: {date}
91**Files Reviewed**: {count}
92 
93### Critical Findings ({count})
94 
95#### [CR-001] {Title}
96 
97**Location**: `{file}:{line}`
98**Dimension**: {Security/Performance/etc.}
99**Description**: {what was found}
100**Impact**: {what could happen}
101**Fix**: {recommended remediation}
102 
103### High Findings ({count})
104 
105...
106 
107### Medium Findings ({count})
108 
109...
110 
111### Low Findings ({count})
112 
113...
114 
115### Summary
116 
117| Dimension | Critical | High | Medium | Low | Total |
118| ------------ | -------- | ----- | ------ | ----- | ------ |
119| Security | 1 | 2 | 3 | 0 | 6 |
120| Performance | 0 | 1 | 4 | 2 | 7 |
121| Architecture | 0 | 0 | 2 | 3 | 5 |
122| **Total** | **1** | **3** | **9** | **5** | **18** |
123 
124### Recommendation
125 
126{Overall assessment and prioritized action items}
127```
128 

Reviews

Installed this one?Write the first review and take the Trailblazer badge.

Reviews only open after a real install, so this is empty — and we leave it empty rather than invent one.

Alternatives

Also in Data & AI