From evaluation-tools
Expert evaluation of database schema designs using multi-perspective analysis. PROACTIVELY activate for: (1) Reviewing database schema designs, (2) Comparing alternative schema approaches, (3) Identifying normalization issues, (4) Assessing scalability and performance implications, (5) Evaluating data integrity constraints, (6) Analyzing schema evolution capabilities. Triggers: "evaluate database schema", "review db design", "assess data model", "compare schema approaches", "check normalization", "database design review", "analyze table structure", "review ER diagram", "evaluate data architecture"
How this skill is triggered — by the user, by Claude, or both
Slash command
/evaluation-tools:database-schema-evaluatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Comprehensive evaluation of database schema designs using expert panel analysis from multiple technical perspectives.
Comprehensive evaluation of database schema designs using expert panel analysis from multiple technical perspectives.
Purpose: Understand the schema structure, business requirements, and evaluation scope.
Actions:
Output Template:
schema_context:
entities: [list of main tables/collections]
relationships: [1:1, 1:N, N:M relationships]
constraints: [PKs, FKs, unique, check constraints]
indexes: [existing or proposed indexes]
business_domain: [domain context]
scale_expectations:
initial_volume: [expected records]
growth_rate: [expected growth]
read_write_ratio: [expected ratio]
specific_concerns: [any highlighted areas]
Purpose: Instantiate domain experts with relevant database perspectives.
Expert Personas:
Data Architect
Performance Engineer
Data Integrity Guardian
Evolution Strategist
Operations Specialist
Purpose: Each expert evaluates the schema from their specialized perspective.
Evaluation Framework:
expert_evaluation:
expert: [Expert Name]
perspective: [Their focus area]
strengths:
- [Specific strength with rationale]
- [Another strength with example]
concerns:
- issue: [Specific concern]
severity: [critical|high|medium|low]
rationale: [Why this matters]
recommendation: [How to address]
opportunities:
- [Improvement opportunity]
- [Optimization suggestion]
risk_assessment:
- risk: [Potential future problem]
likelihood: [high|medium|low]
impact: [high|medium|low]
mitigation: [Suggested approach]
score: [0-10 from this perspective]
confidence: [0-1 confidence in assessment]
Evaluation Criteria by Expert:
| Expert | Primary Criteria | Secondary Criteria |
|---|---|---|
| Data Architect | Normalization level, Design patterns | Naming conventions, Documentation |
| Performance Engineer | Index efficiency, Query complexity | Join paths, Denormalization benefits |
| Data Integrity Guardian | Constraint coverage, Referential integrity | Validation rules, Orphan prevention |
| Evolution Strategist | Migration simplicity, Extensibility | Backward compatibility, Version strategy |
| Operations Specialist | Backup feasibility, Maintenance overhead | Monitoring capability, Recovery time |
Purpose: Synthesize perspectives and identify consensus/conflicts.
Deliberation Process:
Conflict Resolution Matrix:
conflicts:
- conflict: [Description of disagreement]
expert_1: [Position and rationale]
expert_2: [Alternative position]
resolution: [Recommended approach considering tradeoffs]
business_impact: [What this means for the system]
Purpose: Generate quantitative assessment across dimensions.
Scoring Dimensions:
| Dimension | Weight | Factors |
|---|---|---|
| Correctness | 25% | Normalization, integrity, consistency |
| Performance | 20% | Query efficiency, scalability potential |
| Maintainability | 20% | Clarity, documentation, operational simplicity |
| Flexibility | 15% | Extensibility, migration paths |
| Robustness | 10% | Error handling, constraint coverage |
| Security | 10% | Access control, audit capability |
Scoring Algorithm:
dimension_score = Σ(expert_score × expert_weight) / Σ(expert_weights)
overall_score = Σ(dimension_score × dimension_weight)
confidence = min(expert_confidences) × consensus_factor
Purpose: Deliver actionable evaluation with clear recommendations.
# Database Schema Evaluation Report
## Executive Summary
- **Overall Score:** [X/10]
- **Confidence:** [X%]
- **Recommendation:** [APPROVE|APPROVE_WITH_CONDITIONS|REVISE|REJECT]
- **Key Strengths:** [Top 3 strengths]
- **Critical Issues:** [Top 3 concerns if any]
## Schema Overview
[Brief description of schema purpose and structure]
## Expert Evaluations
### Data Architecture Assessment
[Data Architect findings]
- **Score:** X/10
- **Key Findings:** [Bullets]
### Performance Analysis
[Performance Engineer findings]
- **Score:** X/10
- **Key Findings:** [Bullets]
### Data Integrity Review
[Data Integrity Guardian findings]
- **Score:** X/10
- **Key Findings:** [Bullets]
### Evolution Capability
[Evolution Strategist findings]
- **Score:** X/10
- **Key Findings:** [Bullets]
### Operational Assessment
[Operations Specialist findings]
- **Score:** X/10
- **Key Findings:** [Bullets]
## Consolidated Findings
### Strengths
1. [Major strength with supporting expert consensus]
2. [Another strength]
### Critical Issues
1. **[Issue Name]**
- Severity: [Critical/High/Medium/Low]
- Impact: [Description]
- Recommendation: [Specific action]
### Improvement Opportunities
1. [Opportunity with expected benefit]
2. [Another opportunity]
## Tradeoff Analysis
[Discussion of key design tradeoffs and recommendations]
## Risk Assessment
| Risk | Likelihood | Impact | Mitigation Strategy |
|------|------------|--------|-------------------|
| [Risk 1] | High/Medium/Low | High/Medium/Low | [Strategy] |
## Recommendations
### Immediate Actions
1. [Required change before deployment]
2. [Another critical change]
### Short-term Improvements (1-3 months)
1. [Important but not blocking]
### Long-term Considerations (3+ months)
1. [Future optimization]
## Detailed Scoring Matrix
| Dimension | Score | Weight | Weighted Score | Notes |
|-----------|-------|--------|---------------|-------|
| Correctness | X/10 | 25% | X.XX | [Key factors] |
| Performance | X/10 | 20% | X.XX | [Key factors] |
| Maintainability | X/10 | 20% | X.XX | [Key factors] |
| Flexibility | X/10 | 15% | X.XX | [Key factors] |
| Robustness | X/10 | 10% | X.XX | [Key factors] |
| Security | X/10 | 10% | X.XX | [Key factors] |
| **Total** | **X/10** | **100%** | **X.XX** | |
## Appendices
### A. Specific Technical Recommendations
[Detailed technical suggestions with examples]
### B. Alternative Approaches Considered
[If multiple schemas were compared]
### C. References and Best Practices
[Relevant design patterns, articles, or standards]
| Parameter | Default | Options | Description |
|---|---|---|---|
evaluation_depth | comprehensive | quick, standard, comprehensive | Level of analysis detail |
focus_areas | all | performance, integrity, normalization, operations | Specific areas to emphasize |
database_type | relational | relational, document, graph, timeseries | Database paradigm |
include_alternatives | false | true, false | Generate alternative schema suggestions |
comparison_mode | single | single, multiple | Evaluate one or compare multiple schemas |
request: Evaluate this e-commerce database schema
params:
evaluation_depth: comprehensive
focus_areas: [performance, normalization]
database_type: relational
output: Full evaluation report with performance focus
request: Compare normalized vs denormalized inventory schemas
params:
comparison_mode: multiple
focus_areas: [performance, maintainability]
output: Comparative analysis with tradeoff matrix
request: Evaluate schema for microservices migration
params:
focus_areas: [operations, flexibility]
include_alternatives: true
output: Evaluation with migration-focused recommendations
Inputs From:
Outputs To:
From @core/technique-taxonomy.yaml:
This skill leverages the cognitive advantages of:
npx claudepluginhub agentient/vibekit --plugin evaluation-toolsDesigns and documents database schemas with entity relationships, table definitions, constraints, indexes, and access patterns. Useful when modeling entities or planning data models.
Reviews and designs database schemas with normalization (1NF-BCNF), denormalization, multi-tenancy patterns, PK strategies (UUID v7, ULID, KSUID), soft deletes, temporal tables (SCD), audit trails, evolution, naming, data types, anti-patterns. For new schemas, reviews, migrations.
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->