Skip to content

mattgierhart/PRD-driven-context-engineering / .claude/skills/prd-v05-technical-stack-selection

prd-v05-technical-stack-selection

Verified

Determine technologies needed to build the product, making build/buy/integrate decisions during PRD v0.5 Red Team Review. Handles both greenfield and brownfield contexts. Triggers on requests to select tech stack, evaluate technologies, make build vs. buy decisions, discover existing assets, or when user asks "what technologies?", "select tech stack", "build or buy?", "what do we reuse?", "existing stack", "technical decisions", "what tools do we need?", "evaluate solutions". Consumes FEA- (features), SCR- (screens), RISK- (constraints). Outputs TECH- entries with decisions, rationale, and trade-offs. Feeds v0.6 Architecture Design.

FileKindSize
SKILL.mdskill md19.2 KB
assets/evaluation-scorecard.mdmarkdown2.0 KB
assets/tech-reuse.mdmarkdown1.7 KB
assets/tech.mdmarkdown2.3 KB
references/brownfield.mdmarkdown3.7 KB
references/examples.mdmarkdown9.6 KB

assets/evaluation-scorecard.md

View on GitHub
# Technology Evaluation Scorecard

Use this when comparing Buy/Integrate options.

## Scorecard Template

| Criterion | Weight | Option A | Option B | Option C |
|-----------|--------|----------|----------|----------|
| **Fit** (solves our need) | 25% | /5 | /5 | /5 |
| **Cost** (at scale) | 20% | /5 | /5 | /5 |
| **Complexity** (integration effort) | 20% | /5 | /5 | /5 |
| **Lock-in** (switching cost) | 15% | /5 | /5 | /5 |
| **Maturity** (production-ready) | 10% | /5 | /5 | /5 |
| **Support** (help available) | 10% | /5 | /5 | /5 |
| **Weighted Total** | 100% | | | |

## Scoring Guide

### Fit (25%)
- 5: Solves need perfectly, no gaps
- 4: Solves most needs, minor workarounds
- 3: Adequate, some limitations
- 2: Significant gaps
- 1: Poor fit

### Cost (20%)
- 5: Free or negligible at scale
- 4: Reasonable, predictable pricing
- 3: Moderate cost
- 2: Expensive but justifiable
- 1: Prohibitively expensive at scale

### Complexity (20%)
- 5: Drop-in integration, <1 day
- 4: Straightforward, 1-3 days
- 3: Moderate effort, 1 week
- 2: Significant work, 2+ weeks
- 1: Major undertaking

### Lock-in (15%)
- 5: Data portable, easy to switch
- 4: Some effort to migrate
- 3: Moderate switching cost
- 2: Significant migration work
- 1: Effectively locked in

### Maturity (10%)
- 5: Battle-tested, excellent docs
- 4: Production-ready, good docs
- 3: Stable, adequate docs
- 2: Some rough edges
- 1: Immature, poor docs

### Support (10%)
- 5: Excellent support + community
- 4: Good support options
- 3: Adequate support
- 2: Limited support
- 1: No support

## Example Completed Scorecard

**Evaluating: Authentication Service**

| Criterion | Weight | Clerk | Auth0 | Firebase Auth |
|-----------|--------|-------|-------|---------------|
| **Fit** | 25% | 5 | 5 | 4 |
| **Cost** | 20% | 4 | 3 | 5 |
| **Complexity** | 20% | 5 | 3 | 4 |
| **Lock-in** | 15% | 3 | 3 | 2 |
| **Maturity** | 10% | 4 | 5 | 5 |
| **Support** | 10% | 4 | 5 | 3 |
| **Weighted Total** | 100% | **4.3** | **3.8** | **3.8** |

**Decision**: Clerk — Best developer experience, good fit, reasonable cost.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 197kUpdated Claude CodeCodexVerifiedInstall