By TBK Labs · For Claude Code

Describe your idea.
Get a production-ready plan.

A 65-section project planning framework that turns a product idea into fully-specified architecture, tasks, and sprint plans — ready to build. 100+ autopilot steps. 13 phases. One command.

2,100+
Files
630+
Templates
100+
Steps
27
Domain Packs
Overview
What is the Master Starter Kit?
The Master Starter Kit is a planning framework that lives inside your project. You tell Claude Code about your product idea, and the Kit orchestrates a structured planning process — research, architecture, design, task generation, quality enforcement — producing hundreds of specification documents that make your codebase buildable from day one.

The Kit doesn't write code. It produces the blueprints. Service specs, screen specs, API contracts, task files, sprint plans, design systems, testing strategies, and deployment configs. When it's time to build, the GSD execution engine reads those specs and turns them into working software.

One command to start

Drop the Kit into your project directory and run /kit in Claude Code. The orchestrator detects your project's maturity — greenfield, existing codebase, or pivot — and routes you to the right path automatically.

From there, it's a guided process. The Kit asks questions, you answer. It generates specs, you approve. At every major checkpoint (called "gates"), it pauses for your sign-off before continuing.

$ claude
> /kit

// Pre-flight checks...
Health check passed
Context verified
Version current

// Maturity detection...
Greenfield detected
Starting discovery intake

GATE 0 Approve path? [y/n]
Process
How it works
The Kit runs through 13 phases, each producing specific deliverables. You control the pace — it never proceeds past a gate checkpoint without your approval.
Phase 0–1
Discover
~1–2 hours
Intake interview, domain classification, version verification, creative expansion
Phase 2
Research
~2–4 hours
10-round adversarial tribunal: competitors, personas, feasibility, risks
Phase 3–4
Design
~3–6 hours
Architecture, service specs, screen specs, API contracts, workflows
Phase 5–8
Plan
~6–12 hours
Task files, sprint plans, design system, quality gates, testing
Phase 9–10
Extend
~4–8 hours
Marketing, legal, financial modeling, BI, dashboards, SEO
Phase 11
Harden
~3–5 hours
17 rounds of auditing, enhancement, depth verification, expansion
Phase 12
Build & Ship
Variable
GSD execution engine, CI/CD, monitoring, feedback, autonomous loop
Intelligence
Domain-aware from the start
The Kit doesn't treat all projects the same. During intake, it classifies your project into domains (industry verticals) and categories (product shapes), then loads specialized knowledge that shapes every downstream decision.

27 domains × 27 categories

Domains and categories compose additively — a healthcare marketplace gets both the healthcare domain pack and the marketplace category pack. Rules stack, questions merge, entities combine. No artificial branching that forces you to choose.

Each domain pack includes specialized intake questions, domain personas, business rules, regulatory context, entity definitions, and tribunal research rounds. Each category pack adds product-shape patterns, architecture decisions, and UX conventions.

Domains

Healthcare Fintech Insurance Legal Automotive Real Estate Education Logistics Construction Agriculture Energy Hospitality Food Fitness Media Gaming HR Government Nonprofit Manufacturing Retail Telecom Cybersecurity Climate Sports Pets Creative

Categories

SaaS Marketplace E-Commerce B2B Platform Consumer App Content Platform Dev Tools Internal Tool API Product Mobile-First IoT Platform AI Product Social Network Booking Platform CRM ERP LMS CMS Collaboration Automation Analytics Data Platform

Intersections are real. An automotive SaaS marketplace gets all three packs — automotive domain rules, SaaS multi-tenancy patterns, and marketplace two-sided economics. The Kit composes them, deduplicates overlapping questions, merges personas, and produces a unified specification that respects all three contexts.

Output
What the Kit produces
By the end of the process, your project has a complete dev_docs/ directory with everything needed to start building — or hand off to a team.

Service Specifications

One per backend service. Business rules, API endpoints, data models, error handling, auth requirements. Scored for depth — minimum 2,000 words, 10+ business rules, 8+ endpoints per spec.

Architecture

Screen Specifications

Every screen in the application with component trees, state shapes, interactions, responsive behavior, and accessibility requirements. Includes domain-specific design patterns.

Design

API Contracts

Full endpoint documentation with request/response shapes, validation rules, error codes, rate limits, and authentication. Generated from service specs and cross-validated.

Architecture

Task Files & Sprint Plans

Concrete development tasks with acceptance criteria, file plans, test requirements, effort estimates, and 8-layer coverage checklists. Grouped into integration units and sequenced into sprints.

Planning

Design System

Design direction document with color tokens, typography scale, spacing system, layout patterns, animation tokens, accessibility requirements, responsive breakpoints, and interaction patterns.

Design

Deep User Workflows

End-to-end workflow specifications with full screen state, component trees, API calls, UX reasoning, and every decision branch. Each workflow includes a matching Playwright E2E test.

Design

Tribunal Research

60–100 research files from a 10-round adversarial process covering competitors, personas, technical feasibility, market analysis, and domain-specific research rounds.

Research

Quality & Testing

17 enforcement gates, proof artifact collection, design compliance verification, responsive screenshot capture, and Definition of Done validators. Mechanically enforced — not documentation.

Quality

Business Operations

Marketing plans, legal documents (privacy policy, ToS, DPA), financial models, BI dashboards, SEO strategy, support platform setup, and incident response runbooks.

Operations
Coverage
65 sections, 550+ templates
The Kit covers every aspect of taking a product from idea to production — and beyond. Each section contains templates, generators, and examples.
Section What It Covers Key Templates
Discovery & IntakeProject brief, domain classification, intake questions, creative expansionProject brief, domain classifier, 54 domain/category packs
Tribunal Research10-round adversarial research + 6 domain-conditional roundsCompetitive analysis, persona cards, feasibility verdicts
ArchitectureDatabase design, API design, state management, component libraryDB schema, migration plan, component library, API patterns
DocumentationService specs, screen specs, design docs, state files, contractsService spec, screen spec, integration unit, design direction
Phase PlanningPhase templates, task templates, sprint planningTask file, phase plan, timeline, dependency map
Dev InfrastructureDocker, monorepo, linting, hooks, CI/CD, Claude Code configDocker compose, turbo config, eslint, pre-commit hooks
Development WorkflowSession rituals, onboarding, verification loops, GSD protocolSession ritual, verification macros, GSD verification protocol
UI Design SystemDesign tokens, components, anti-slop rules, domain patternsDesign tokens, 27-domain design pattern library
Quality & TestingTest configs, enforcement gates, design compliance, proof artifacts17 enforcement gates, 8-layer task verification, DoD validator
Generators54 auto-generation prompts with depth requirementsService hub, screen catalog, Context Bible, battle cards
MobilePlatform selection, mobile UI, native features, mobile deploymentMobile architecture, push notifications, offline-first
Marketing & GrowthSEO, content, email, social, launch planning, PLGLaunch checklist, content calendar, growth loops
Legal & PrivacyPrivacy policy, ToS, DPA, EULA, GDPR, data flow mappingPrivacy policy, cookie policy, consent management
FinancialRevenue projections, unit economics, runway, investor docsFinancial model, pitch deck, cap table, term sheets
OperationsIncidents, support, billing, BI, dashboards, experimentsRunbooks, SLA templates, dashboard specs, A/B framework
Hardening17 rounds of audit, enhancement, depth verification, expansionAudit checklists, enhancement logs, expansion templates
Execution
From plan to production
After planning completes, the Kit transitions into a lifecycle engine. Build, ship, monitor, collect feedback, and iterate — with autonomous bug-fix loops.

GSD: Sprint-scoped execution

The GSD engine reads task files and builds features sprint by sprint — 20–40 tasks per session. Each task goes through an 8-gate verification sequence before it can be marked complete: type check, tests, lint, build, design compliance, screenshots, state completeness, and integration verification.

Failed tasks get 3 retry attempts with automated fixing. After 3 failures, the task is escalated to BLOCKED status with a full diagnostic report.

// GSD task flow

1. Read task + load context
2. Read spec references
3. Plan implementation
4. Write code
5. Pre-completion gates
   5a TypeScript + Tests + Lint + Build
   5b Design token compliance
   5c Screenshots @ 4 breakpoints
   5d State completeness + Integration
   5e DoD validator (10 points)
6. Collect proof artifacts
7. Update state files
8. Next task

// If gate fails: retry (max 3)
// If still fails: → BLOCKED

Autonomous iteration loop

After shipping, the Kit scaffolds monitoring (Sentry, analytics, uptime), feedback collection (widgets, NPS, knowledge base), and a signal-driven iteration loop. Bugs trigger automatic fix-test-deploy cycles. User feedback aggregates into the next sprint plan.

The lifecycle engine runs as long as you want it to — or you can detach and manage the project manually at any point.

BUILDSHIPWATCHCOLLECTLOOP
  ↑                                                 │
  └──────────────────────────────────────────────┘

// Signals
bug_report → auto-fix → test → deploy
feedback   → triage → sprint backlog
metrics    → alert → investigate
uptime     → page → runbook
Flexibility
Three paths, one Kit
The Kit detects your project's maturity at Step 0.5 and routes you to the right path.

Greenfield

Starting from scratch. Full 100+ step process from discovery through build. Every section applies. The Kit produces the complete specification and lets you build with full confidence.

Enhance

Existing codebase that needs improvement. The Kit audits what you have, scores it, identifies gaps, and generates tasks to bring the project up to spec. Skips discovery, goes straight to audit.

Repurpose

Pivoting or forking an existing application to a new vertical. The Kit maps what can be reused, what needs to be rebuilt, and produces a migration plan with the new domain's requirements layered in.

Quality
You stay in control
Gate checkpoints pause the Kit for your approval at every major transition. You choose the level of control.
Gate Mode How It Works Best For
ManualEvery gate pauses. You review and approve each one.First project, regulated domains, learning the Kit
Semi-AutoStructural gates pause, informational gates auto-pass.Experienced users, standard projects
AutoMost gates auto-pass. Only major milestones pause.Repeat projects, tight timelines
AutopilotFull autonomous execution. Pauses only at session boundaries.Rebuilding a well-understood product

Domain-adaptive gates. Gate criteria aren't one-size-fits-all. Healthcare projects get HIPAA compliance checks. Fintech projects get PCI-DSS verification. Marketplace projects get dual-side coverage validation. The criteria stack based on your project's domain and category classification.