TypeSafe Agent Skills

# MISSION: Scaffold "TypeSafe Agent Skills" Production Architecture
You are an expert Senior Staff Software Architect and Full-Stack Engineer. Your mission is to scaffold and implement a production-grade, highly reliable, and modular codebase following the proven architecture of **TypeSafe Agent Skills**.
---
## 1. PROJECT SPECIFICATIONS & BENCHMARK
- **Reference Architecture**: TypeSafe Agent Skills
- **What It Does**: TypeSafe Agent Skills is TypeSafe AI's official Agent Skill that teaches Claude Code, Codex and other coding agents to build with Jev, its System One model, by reading live docs and designing typed questions.
- **Domain & Category**: Agent Skill
- **Production Scale**: 6-20 people
- **Development Mode**: CLASSIC
- **Architectural Rationale**: Shipping one SKILL.md that points agents at live Markdown docs, installable as a Claude Code plugin or via skills.sh, keeps agent guidance current without an MCP server and without copying version-specific API details.
- **Live Website Reference**: https://docs.typesafe.ai/agent-skill
- **Source Repository**: https://github.com/typesafe-ai/skills
---
## 2. PRODUCTION TECH STACK
- **Full Stack Array**: Jev, Claude Code, Agent Skills, Markdown
- **Primary Language(s)**: Markdown
- **License of the reference repo**: MIT
- **Tooling, testing & ops**: Agent Skills — One skill, skills/typesafe-ai/SKILL.md, in the open Agent Skills format with name, license and description frontmatter.; Claude Code — Installable as a Claude Code plugin through the repository's own plugin marketplace manifest.; skills.sh — Installs the same skill into other agents with npx skills add typesafe-ai/skills --skill typesafe-ai.; Jev — The TypeSafe System One model the skill teaches agents to build with: Choice, Score and Noul questions over state.
---
## 3. KEY ARCHITECTURAL DECISIONS (audited from https://github.com/typesafe-ai/skills @ 65a39f3)
1. **A skill instead of an MCP server**: TypeSafe distributes its integration knowledge as an Agent Skill that coding agents load while writing code, rather than as an MCP server that exposes Jev calls as tools; the repository contains only the skill, a license, a README and plugin manifests.
2. **Point at live docs instead of copying them**: SKILL.md tells agents that the live TypeSafe docs are the source of truth, to start from the llms.txt index, to fetch pages as Markdown by appending .md, and to avoid inventing version-dependent details when the docs are unreachable.
3. **One skill, several install paths**: The README offers a Claude Code plugin install (claude plugin marketplace add typesafe-ai/skills, then claude plugin install typesafe@typesafe-ai) and an npx skills add command for other agents, project-local by default with -g for global installs.
4. **Guidance on shape, not only syntax**: Besides API pointers, SKILL.md lists patterns (route and fill arguments, select instead of generate, find and judge evidence, verify and escalate) and rules for designing questions, such as one narrow judgment per question and keeping math and exact lookups in code.
---
## 4. NON-NEGOTIABLE ARCHITECTURAL GUARDRAILS
1. **Monorepo & Modular Separation**:
   - Structure as a Turborepo monorepo with strict package boundaries:
     - `apps/web`: Application UI, routing, layouts, and server endpoints.
     - `packages/ui`: Shared design tokens, CSS variables, and Radix UI primitive components.
     - `packages/db`: Database schemas, client singleton, declarative migrations, and seed scripts.
     - `packages/config`: Shared TypeScript, ESLint, and build configurations.
2. **Strict Type Safety & Zero `any` Policy**:
   - Enable `strict: true`, `noImplicitAny: true`, and `strictNullChecks: true`.
   - Validate ALL external inputs, API request bodies, and query parameters with **Zod** schemas before execution.
3. **Frontend & Rendering Guidelines**:
   - Isolate interactive UI state to leaf components. Keep core pages lightweight and performant.
4. **Design System & Aesthetics**:
   - Keep every color, radius, shadow and font in a single token file (CSS variables) and consume tokens everywhere; never hardcode hex values in components.
   - Prefer crisp 1px borders and one subtle shadow scale over blurry default shadows. Pair one sans-serif for body/headings with one monospace for tags, badges, metrics, and code.
5. **Data Layer & Reliability**:
   - Write declarative schema definitions with foreign keys, composite indexes on queried filters, and automated timestamp triggers.
   - Use connection pooling and prepared statements for serverless database execution.
---
## 5. STEP-BY-STEP SCAFFOLDING ROADMAP
- **Phase 1: Workspace & Root Config**: Initialize package manager, monorepo configuration (`turbo.json`, `tsconfig.base.json`, `package.json`).
- **Phase 2: Database Schema & Client**: Set up the data layer: client, connection pool, models, and migration scripts.
- **Phase 3: Design Tokens & UI Primitives**: Build accessible `Button`, `Input`, `Card`, `Badge`, and layout wrappers inside `packages/ui`.
- **Phase 4: Core Application Routes & Handlers**: Implement primary authentication, user session handling, and application routes.
- **Phase 5: Quality Assurance & Build Verification**: Run `tsc --noEmit`, ESLint, Prettier, and smoke test suites to ensure zero compilation or runtime errors.
---
## 6. EXECUTION INSTRUCTIONS
1. Review all specifications, architectural guardrails, and stack choices above.
2. Present the full monorepo directory tree structure.
3. Systematically generate the complete, production-ready codebase according to the 5-phase roadmap above — starting with the root workspace setup, followed by the database schema, UI design system package, and full-stack application routes until the repository is fully scaffolded and ready to run.