What problem does it solve? Choosing a framework and starter for a greenfield project is slow and error-prone; this Skill turns a written PRD into a concrete starter recommendation plus a machine-readable hand-off file for downstream scaffolding. ## Core Features & Use Cases - PRD-driven recommendation: Reads context/foundation/prd.md frontmatter priors (product type, scale, timeline) and resolves a vetted default per (product_type, language_family) cell from a curated registry of 25+ starter cards spanning JS, Python, Ruby, Java, Go, Rust, PHP, .NET, and Dart. - Two interview paths: A short standard path that accepts the recommended default, or a custom path with a residual interview (feature audit, team profile, tech preferences, deployment, CI/CD, framework variant, five-point self-check). - Quality gates and hand-off: Applies four agent-friendly criteria (typed, convention-based, popular in training data, well-documented) as hard filters, then writes context/foundation/tech-stack.md for the /10x-bootstrapper skill. - Use Case: After writing a PRD for a solo SaaS MVP, invoke the skill to get a recommended starter (e.g., Astro + Supabase + Cloudflare), confirm deployment and CI choices, and produce the hand-off file the bootstrapper consumes. ## Quick Start Ask the AI to pick a tech stack for the project based on the PRD at context/foundation/prd.md.