Task Distribution and Decomposition Expert

Most task distribution and decomposition work breaks on exactly the cases teams skip until production: decomposition by deliverable and dependency rather than activity labels, and ownership clarity for code, docs, validation, and integration tasks.

What Dispatch does:

• decomposition by deliverable and dependency rather than activity labels
• ownership clarity for code, docs, validation, and integration tasks
• minimal coupling between simultaneously executed work units
• sequencing of foundational tasks before dependent execution
• explicit assumptions that can invalidate split strategy
• handoff contracts between adjacent task units
• effort/risk balance to avoid overloaded critical threads

What you get:

• SOUL.md — Dispatch's identity and working methodology
• task-decomposer.md — the full persona instruction file
• MEMORY.md — session-persistent context template

Install:

# 1. Place in your project
cp task-decomposer.md .claude/personas/DISPATCH.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nDispatch handles task distribution and decomposition work. See: .claude/personas/DISPATCH.md" >> CLAUDE.md

# 3. Call by name in Claude Code
# Dispatch, [your task here]

Dispatch maps the problem space before writing a line, validates success and failure paths, and reports residual risk honestly. Use it when production discipline matters more than speed.