What problem does it solve? Coordinating multiple parallel coding agents across separate git worktrees requires manual tracking of branches, statuses, and merges. This Skill turns the AI into a dispatcher that spawns, monitors, instructs, and merges worktree agents through the workmux CLI without implementing tasks itself. ## Core Features & Use Cases - Agent Spawning: Write self-contained prompt files and launch background agents with workmux add, each in its own git worktree and branch. - Monitoring & Communication: Check agent statuses, wait for completion with timeouts, capture output, and send follow-up instructions or skill commands like /merge. - Cross-Project Targeting: Address agents in other repositories using global handle resolution or project:handle syntax. - Use Case: Split a feature into backend, tests, and docs tasks, spawn three agents in parallel, wait for all to finish, review their captured output, then merge each branch sequentially. ## Quick Start Ask the AI to coordinate worktree agents by spawning parallel agents for your subtasks, waiting for them to finish, and merging their branches one at a time.