Rudolf S.

Factory loop orchestrator. Reads a decomposition manifest, spawns isolated code agents and evaluation agents per unit, manages the retry cycle until scenario satisfaction meets threshold or max iterations is reached.

Create comprehensive specifications from brief descriptions while managing the workflow.

Decomposes features into factory-ready artifacts for streamlined development.

Generate and maintain documentation for code, APIs, and project components

The Agentic Startup is a multi-agent AI framework that streamlines software development through spec-driven processes.

Create and validate solution design documents (SDD) for architecture and technical decisions.

Validate specifications and implementations for compliance and quality assurance.

Streamline the creation, auditing, and conversion of skills for Claude Code.

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.

Create or update project constitutions with tailored governance rules through a discovery-based approach.

Manage and track specification directories with automated scaffolding and decision logging.

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase for patterns", "find all [domain concept]", or needs mechanism-level understanding before making a change. Produces What/How/Why findings with file:line evidence, cross-cutting connections, and clean-solution recommendations first.

Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)

Refactor, simplify, or clean up code for improved maintainability without changing business logic

Systematically diagnose and resolve bugs through conversational investigation and root cause analysis

Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.

Create and validate product requirements documents (PRD) efficiently.