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/tech-reuse.md

View on GitHub
# TECH- Template (Reuse/Extend)

Use for Reuse and Extend decisions where an existing asset covers the need.

```
TECH-XXX: [Technology/Capability Name]
Category: [Reuse | Extend]
Layer: [Derived from capability area]
Purpose: [What problem this solves for the new product]

Reuse From: [Source product or asset — e.g., "Product-A — Keycloak deployment"]
Reuse Scope: [Full reuse | Extend | Shared instance | Pattern only]
Current State: [What exists today and how it's deployed]
Changes Needed: [What the new product needs that doesn't exist yet, or "None" for full reuse]

Shared or Separate: [Shared deployment (separate namespace/realm) | Separate instance | Same instance]

Features Served: [FEA-XXX, FEA-YYY]
Risk Constraints: [RISK-XXX if any]

Cost: [Incremental cost — often $0 for reuse, or cost of extending]
Integration Complexity: [Low | Medium | High]
Lock-in Risk: [Already committed — note if this matters]

# Optional:
Product Family Notes: [Cross-product impact, SSO considerations, shared data]
```

## When to Use This Template

| Situation | Use This Template |
|-----------|-------------------|
| Sibling product already runs this service | Yes — Reuse |
| Service exists but needs new features for this product | Yes — Extend |
| Service exists but is wrong for this product | No — use standard template with Category: Replace |
| No existing asset | No — use standard template |

## Checklist Before Adding

- [ ] Verified the existing asset actually works for this use case
- [ ] Confirmed with team that the asset is still actively maintained
- [ ] Documented any changes needed (even if "None")
- [ ] Shared vs. separate deployment decision is explicit
- [ ] Features Served references are correct
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