vinzenz

Break down a PRD or CRD into self-contained implementation tasks for LLM execution. Use when you have a PRD/CRD file and want to generate executable task files for autonomous implementation.

Incremental PROJECT.md update using git diff. Only re-analyzes changed areas for efficient context maintenance.

Analyze the impact of a proposed change on an existing codebase. Identifies affected files, features, and potential breaking changes.

Deep codebase investigation to generate PROJECT.md context. Analyzes architecture, patterns, features, APIs, and schemas.

Orchestrates Change Request Document workflow. Manages context, captures changes, analyzes impact, and generates CRD files.

Handles one batch of tasks. Spawns task agents in parallel using git worktrees, waits for completion, and updates state.

Main entry point for hierarchical task execution. Orchestrates layer-by-layer implementation of PRD tasks with parallel worktree execution.

Independent verification agent using Haiku. Runs verification commands from task XML and reports pass/fail with actionable feedback.

Creates contextual design briefs before any visual work begins. Establishes product purpose, user specificity, design principles, and anti-goals. Prevents generic "template" design by requiring specific context.

Simulates the professional design critique process. Forces questioning of every design decision, validates intentionality, checks optical balance, and ensures designs serve specific product purposes rather than following generic patterns.

Forces documentation of the reasoning behind every significant design decision. Creates a decision log that explains WHY choices were made, alternatives considered, and trade-offs accepted. Prevents unjustified "default" choices.

Reviews designs for optical balance issues that mathematical precision misses. Covers typography kerning, visual alignment, spacing rhythm, color weight, and the human touch that distinguishes professional design from AI-generated output.

Multi-phase workflow orchestration pattern for main agents. Enables structured planning, delegation to sub-agents, parallel execution, and result aggregation.