skills.rest
DarkCodePE
DarkCodePECOMMUNITY
Explore all skills by this author →
𝕏@natural_select1GitHub

claude-devfleet

Orchestrate multi-agent coding tasks in isolated worktrees with structured reports.

Updated Aug 27, 2026
Search Tags:#automation#planning#worktrees#multi-agent#parallel#devfleet
One-click install
npx skills add https://github.com/DarkCodePE/quipu --skill claude-devfleet-darkcodepe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-devfleet
Source: https://github.com/DarkCodePE/quipu/tree/main/docs/arquetipo/deliverables/skills/_optional/claude-devfleet
Command: npx skills add https://github.com/DarkCodePE/quipu --skill claude-devfleet-darkcodepe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

Core Features & Use Cases

  • Plan projects with plan_project(prompt), create_project, and create_mission to define DAGs
  • Dispatch missions with dispatch_mission and auto_dispatch to run many agents in parallel
  • Monitor progress using get_dashboard and wait_for_mission/get_mission_status
  • Retrieve structured reports with get_report and summarize outcomes

Quick Start

Plan a project, dispatch the root mission, and monitor progress until completion.

Frequently Asked Questions about claude-devfleet

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multi-agent coding tasks in parallel using isolated worktrees?▼

Multi-agent coding tasks run in parallel by dispatching missions to isolated worktrees, allowing agents to execute independently. You can define task dependencies, monitor progress via dashboards, and retrieve structured reports upon completion.

What is the best way to orchestrate parallel software development with automated dependency management?▼

Orchestrating parallel software development is achieved by planning projects as DAGs and dispatching agents with optional dependencies. The system coordinates task execution automatically, providing dashboards to monitor real-time progress and aggregated reports.

Can I monitor progress and view structured reports for dispatched parallel agents?▼

Yes, monitoring progress and viewing structured reports is supported. You can poll dashboards using get_dashboard, check mission status, and retrieve aggregated outcomes with get_report to summarize results after agents finish.

How do I plan projects and define task dependencies for multi-agent dispatch?▼

Planning projects and defining dependencies involves using plan_project, create_project, and create_mission to build directed acyclic graphs. This structure allows auto_dispatch to execute many parallel agents efficiently.

Do I need any specific dependencies or environments to coordinate multi-agent coding tasks?▼

No external dependencies are required to coordinate multi-agent coding tasks. The environment operates independently to plan projects, dispatch isolated worktrees, and generate structured reports without additional setup.

When should I avoid using parallel agents for software development workflows?▼

Parallel agents should be avoided for software development workflows with highly interdependent, sequential tasks. If isolated worktrees cannot operate independently due to tight coupling, dispatching parallel missions will create complex dependency conflicts.

Related Skills

Explore More Software Engineering Skills→
alexanderopalexanderop

using-git-worktrees

Create isolated git worktrees for feature branches with safety checks.

Community
Advanced
jmaglyjmagly
175

gate-evaluation

Validate phase-gate criteria and generate pass/fail gate reports.

Community
Advanced
TalonT-OrgTalonT-Org
5

implement-worktree-no-merge

Implement a development plan in an isolated Git worktree with phased commits.

Official
Advanced
QunnnnQunnnn

dispatching-parallel-agents

Coordinate parallel delegation of independent tasks across specialized agents.

Community
Intermediate