ReddRadar
Agent skill
comparative-matrix
Generate structured comparisons and decision matrices across analyzed frameworks. Use when (1) comparing multiple frameworks or approaches side-by-side, (2) making architectural decisions between alternatives, (3) creating best-of-breed selection documentation, (4) synthesizing findings from multiple analysis skills into actionable decisions, or (5) producing recommendation reports for technical stakeholders.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/dowwie/comparative-matrix
SKILL.md
Comparative Matrix
Synthesizes analysis outputs into structured decision frameworks.
Process
- Collect analysis outputs from multiple frameworks
- Normalize findings to comparable dimensions
- Generate comparison matrix
- Apply decision heuristics
- Document recommendations with rationale
Comparison Dimensions
Core Dimensions (Always Include)
| Dimension | What to Compare | Decision Criteria |
|---|---|---|
| Typing | Strict (Pydantic) vs Loose (dicts) | Team preference, runtime safety needs |
| Async | Native async vs sync-with-wrappers | Scalability requirements |
| State | Immutable vs mutable | Concurrency safety, debugging |
| Config | Code-first vs config-first | Flexibility vs discoverability |
| Extensibility | Composition vs inheritance | Maintainability, learning curve |
Domain-Specific Dimensions
| Dimension | When to Include |
|---|---|
| Reasoning Pattern | Comparing agent frameworks |
| Memory Strategy | Long-running agents |
| Multi-Agent | Orchestration systems |
| Observability | Production deployments |
| Tool Interface | Custom tool development |
Matrix Template
## Best-of-Breed Matrix: [Analysis Title]
| Dimension | Framework A | Framework B | Framework C | **Recommendation** |
|:----------|:------------|:------------|:------------|:-------------------|
| **Typing** | Pydantic V1, deep nesting | TypedDict, flat | Loose dicts | *Pydantic V2, flat structures* |
| **Async** | Sync core, async wrapper | Native async | Mixed | *Native async required* |
| **State** | Mutable, in-place | Immutable copy | Hybrid | *Immutable preferred* |
| **Config** | YAML + Python | Pure Python | JSON | *Python for type safety* |
| **Extensibility** | Deep inheritance (6 layers) | Composition | Protocols | *Composition + Protocols* |
### Dimension Details
#### Typing
- **Framework A**: Uses Pydantic V1 with deeply nested models (Message → Content → Block → ...)
- Pro: Full validation at boundaries
- Con: Difficult to extend, version migration pain
- **Framework B**: TypedDict with flat structure
- Pro: Simple, fast, IDE support
- Con: No runtime validation
- **Recommendation**: Adopt Pydantic V2 with intentionally flat structures. Use TypedDict for internal types.
[Continue for each dimension...]
Decision Heuristics
Apply these heuristics when recommendations aren't obvious:
Scalability-First
IF high_concurrency_expected:
PREFER native_async
PREFER immutable_state
PREFER stateless_tools
DX-First (Developer Experience)
IF team_is_small OR rapid_iteration:
PREFER simple_inheritance_over_protocols
PREFER code_first_config
PREFER explicit_over_magic
Production-First
IF mission_critical:
PREFER strict_typing
PREFER comprehensive_observability
PREFER explicit_error_boundaries
Output Artifacts
- Summary Matrix - Single-page comparison table
- Detailed Analysis - Per-dimension breakdown with evidence
- Recommendation Document - Actionable decisions with rationale
- Trade-off Log - Documented compromises and their justification
Example Output Structure
comparative-analysis/
├── matrix.md # Summary comparison table
├── dimensions/
│ ├── typing.md # Detailed typing analysis
│ ├── async.md # Concurrency model analysis
│ └── ...
├── recommendations.md # Final decisions
└── tradeoffs.md # Documented compromises
Integration
- Inputs from: All Phase 1 & 2 analysis skills
- Outputs to:
antipattern-catalog,architecture-synthesis
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
aiskillstore/marketplace
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
aiskillstore/marketplace
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
aiskillstore/marketplace
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
aiskillstore/marketplace
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
aiskillstore/marketplace
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
aiskillstore/marketplace
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?