review-synthesis
Aggregate multi-reviewer feedback into consolidated, prioritized, and actionable recommendations
What this skill does
# review-synthesis
Aggregate multi-reviewer feedback into consolidated, actionable recommendations.
## Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "merge reviews" → multi-reviewer feedback synthesis
- "synthesize feedback" → review consolidation
## Purpose
This skill aggregates feedback from multiple reviewers into cohesive, prioritized recommendations by:
- Collecting feedback from parallel review processes
- Identifying consensus and conflicts
- Prioritizing by impact and frequency
- Resolving contradictions with rationale
- Generating actionable synthesis reports
## Behavior
When triggered, this skill:
1. **Collects review inputs**:
- Gather all reviewer feedback files
- Parse structured and unstructured comments
- Identify reviewer roles and expertise areas
2. **Categorizes feedback**:
- Group by feedback type (content, design, technical, legal)
- Tag by severity (blocking, major, minor, suggestion)
- Map to asset sections/elements
3. **Identifies patterns**:
- Find consensus (multiple reviewers agree)
- Detect conflicts (reviewers disagree)
- Note unique insights (single reviewer)
4. **Resolves conflicts**:
- Apply priority rules
- Document both positions
- Provide resolution rationale
- Flag for escalation if needed
5. **Prioritizes actions**:
- Rank by business impact
- Consider implementation effort
- Group quick wins vs major changes
6. **Generates synthesis**:
- Executive summary
- Detailed action items
- Conflict resolution notes
- Approval recommendations
## Review Categories
### Content Reviews
```yaml
content_feedback:
sources:
- content-writer
- editor
- copywriter
- content-strategist
aspects:
- messaging_clarity
- value_proposition
- tone_voice
- cta_effectiveness
- audience_alignment
weight: high
priority_in_conflict: medium
```
### Brand Reviews
```yaml
brand_feedback:
sources:
- brand-guardian
- creative-director
- art-director
aspects:
- visual_identity
- verbal_identity
- brand_consistency
- guideline_compliance
weight: high
priority_in_conflict: high
```
### Technical Reviews
```yaml
technical_feedback:
sources:
- quality-controller
- production-coordinator
- technical-marketing-writer
aspects:
- specifications
- file_formats
- rendering_quality
- platform_compatibility
weight: medium
priority_in_conflict: high_for_blocking
```
### Legal Reviews
```yaml
legal_feedback:
sources:
- legal-reviewer
- legal-liaison
aspects:
- claims_substantiation
- disclosures
- trademark_usage
- regulatory_compliance
weight: critical
priority_in_conflict: highest
```
### Strategic Reviews
```yaml
strategic_feedback:
sources:
- campaign-strategist
- marketing-analyst
- positioning-specialist
aspects:
- campaign_alignment
- competitive_positioning
- market_fit
- kpi_potential
weight: medium
priority_in_conflict: medium
```
## Conflict Resolution Rules
### Priority Hierarchy
```yaml
conflict_resolution:
priority_order:
1: legal_compliance # Always wins
2: brand_guidelines # Strong preference
3: technical_requirements # If blocking
4: strategic_alignment # Business logic
5: content_preference # Style choices
6: design_preference # Aesthetic choices
escalation_triggers:
- legal_vs_brand
- strategy_vs_brand
- multiple_blockers
- no_clear_winner
resolution_methods:
consensus: Majority agreement (3+ reviewers)
expertise: Defer to domain expert
priority: Apply priority hierarchy
escalate: Flag for stakeholder decision
```
### Conflict Types
```yaml
conflict_types:
direct_contradiction:
description: Reviewer A says X, Reviewer B says not-X
resolution: Apply priority hierarchy
documentation: Required
style_preference:
description: Different aesthetic preferences
resolution: Defer to brand/creative director
documentation: Optional
scope_disagreement:
description: Disagree on what needs changing
resolution: Defer to strategic alignment
documentation: Required
priority_disagreement:
description: Agree on issue, disagree on severity
resolution: Take higher severity
documentation: Optional
```
## Synthesis Report Format
```markdown
# Review Synthesis Report
**Asset**: Q1 Product Launch Campaign - Landing Page
**Reviews Collected**: 6
**Date**: 2025-12-08
**Synthesizer**: review-synthesis skill
## Executive Summary
| Metric | Count |
|--------|-------|
| Total Comments | 47 |
| Consensus Items | 28 |
| Conflicts Resolved | 8 |
| Escalations Needed | 2 |
| Blocking Issues | 3 |
| Major Issues | 12 |
| Minor Issues | 25 |
| Suggestions | 7 |
**Overall Assessment**: Asset requires revisions before approval.
## Reviewer Participation
| Reviewer | Role | Comments | Focus Areas |
|----------|------|----------|-------------|
| Sarah Chen | Brand Guardian | 12 | Visual identity, logo usage |
| Marcus Johnson | Editor | 8 | Copy clarity, grammar |
| Elena Rodriguez | Legal Reviewer | 5 | Claims, disclosures |
| David Kim | Campaign Strategist | 10 | Messaging, positioning |
| Amy Liu | Quality Controller | 7 | Technical specs |
| James Wilson | Creative Director | 5 | Overall creative |
## Consensus Items (High Confidence)
### 1. Hero Headline Needs Strengthening
- **Reviewers**: Sarah, Marcus, David (3/6 = consensus)
- **Current**: "Introducing Our New Product"
- **Issue**: Generic, doesn't communicate value
- **Recommendation**: "Cut Your Workflow Time in Half"
- **Priority**: High
- **Effort**: Low (copy change only)
### 2. CTA Button Color
- **Reviewers**: Sarah, Amy, James (3/6 = consensus)
- **Current**: Light gray (#CCCCCC)
- **Issue**: Low contrast, doesn't stand out
- **Recommendation**: Brand green (#00AA55)
- **Priority**: High
- **Effort**: Low
### 3. Missing Privacy Disclosure
- **Reviewers**: Elena (legal = authoritative)
- **Issue**: Form collects email without privacy notice
- **Requirement**: Add privacy policy link
- **Priority**: Blocking
- **Effort**: Low
## Conflicts Resolved
### Conflict 1: Product Image Style
- **Position A** (Sarah, Brand Guardian): Use lifestyle photography
- **Position B** (James, Creative Director): Use product-only shots
- **Resolution**: Lifestyle photography
- **Rationale**: Brand guidelines specify lifestyle imagery for hero sections
- **Priority Rule Applied**: Brand guidelines (priority 2)
### Conflict 2: Headline Tone
- **Position A** (Marcus, Editor): Professional, formal tone
- **Position B** (David, Strategist): Casual, conversational tone
- **Resolution**: Professional with conversational elements
- **Rationale**: Hybrid approach matches brand voice profile (Friendly Professional)
- **Priority Rule Applied**: Brand alignment via voice profile
### Conflict 3: Feature List Length
- **Position A** (David, Strategist): Show all 10 features
- **Position B** (Sarah, Brand Guardian): Limit to top 5
- **Resolution**: Top 5 features with "See all features" link
- **Rationale**: Balances completeness with visual clarity
- **Priority Rule Applied**: Consensus via compromise
## Escalations Required
### Escalation 1: Pricing Display
- **Issue**: Whether to show pricing on landing page
- **Position A** (David): Show pricing for transparency
- **Position B** (Marcus): Hide pricing, focus on value
- **Why Escalated**: Strategic decision beyond reviewer authority
- **Decision Needed From**: Marketing Director
- **Deadline**: Before final approval
### Escalation 2: Competitor Comparison
- **Issue**: Include comparison chart with competitors?
- **Position A** (David): Yes, differentiates product
- **Position B** (Elena): Risk of legal issues without substantiation
- **Why Escalated**: Legal/strategy conflict
- **Decision NRelated in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.