What problem does it solve? Coordinating multiple coding agents on a single project manually is error-prone and slow. This Skill lets you plan a project, dispatch Claude Code agents to work in parallel within isolated git worktrees, monitor their progress, and read structured completion reports through a running Claude DevFleet MCP server. ## Core Features & Use Cases - AI Project Planning: Call plan_project to break a natural-language description into a project with chained missions and dependency DAGs. - Parallel Agent Dispatch: Launch agents with dispatch_mission, with automatic queuing and auto-dispatch of dependent missions as slots free up (default 3 concurrent agents). - Monitoring & Reporting: Track progress with get_mission_status and get_dashboard, then read structured reports via get_report covering files changed, errors, and next steps. - Use Case: Ask to build a REST API with auth and tests; the Skill plans the missions, dispatches the root mission, auto-dispatches dependents after auto-merge, and reports results back to you. ## Quick Start Connect the DevFleet MCP server and ask the assistant to plan and launch a project, for example: plan and build a REST API with authentication and tests using DevFleet.
