What problem does it solve? Choosing a tech stack for a greenfield project is slow and error-prone, especially when the choice must also work well with AI coding agents. This Skill turns a written PRD into a vetted starter recommendation and a machine-readable hand-off file that a downstream bootstrapper can consume to scaffold the project. ## Core Features & Use Cases - PRD-driven recommendation: Reads context/foundation/prd.md frontmatter (product_type, target_scale, timeline_budget) and functional requirements as decision priors, refusing to run without the file on disk. - Two decision paths: A standard path that short-circuits to a vetted recommended default for the (product_type, language_family) cell, and a custom path that walks a residual interview covering features, team profile, preferences, deployment, CI/CD, and a five-point self-check. - Quality-gated registry: Reasons over a language-aware starter registry (JS, Python, Ruby, Java, Go, Rust, PHP, .NET, Dart) applying four agent-friendly gates: typed, convention-based, popular in training data, and well-documented. - Use Case: After finishing a PRD for a solo SaaS MVP, invoke the Skill to get a recommended starter (e.g., an Astro + Supabase + Cloudflare stack), confirm deployment and CI choices, and receive a tech-stack.md hand-off ready for scaffolding. ## Quick Start Ask the assistant to pick a tech stack for your project based on the PRD at context/foundation/prd.md.