parallel

Orchestrate parallel development tasks across isolated worktree agents with PRDs and jsonl context files.

3|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/BaSui01/agentflow --skill parallel-basui01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel
Source: https://github.com/BaSui01/agentflow/tree/main/.codex/skills/parallel
Command: npx skills add https://github.com/BaSui01/agentflow --skill parallel-basui01

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual overhead of coordinating multiple concurrent development efforts by planning tasks, preparing isolated worktree task directories with PRDs and jsonl context files, and dispatching independent coding agents so the main repository remains unchanged.

Core Features & Use Cases

  • Plan-and-dispatch orchestration: Run a Plan Agent to validate requirements, analyze code and specs, generate task directories, and configure branches and scopes.
  • Manual configuration path: For small, well-scoped features, create and initialize task directories, add contextual files, and validate before launching agents.
  • Monitoring and lifecycle: Start, monitor, and clean up worktree agents with status and log commands to observe progress and recover resources.
  • Use Case: Launch parallel worktrees to implement three independent features across backend and frontend modules, each with its own PRD and CI-ready branch.

Quick Start

Ask the orchestrator to "Plan and dispatch a parallel pipeline to implement <feature-name> across the specified modules and start worktree agents."

Frequently Asked Questions about parallel

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

FAQPage Schema
How do I orchestrate parallel multi-agent development without modifying the main repository?

You orchestrate parallel multi-agent development by using a Plan Agent to validate requirements, generate task directories with PRDs and jsonl context files, and dispatch independent coding agents to isolated worktree branches without modifying the main repository.

What is the best way to automate task creation for independent backend and frontend features?

Automating task creation for independent features involves generating isolated task directories, configuring branch scopes, applying requirement validation, and creating jsonl context files to prepare worktree agents for parallel execution.

Can I manually configure worktree task directories for small, well-scoped features?

Yes, you can manually create and initialize worktree task directories, add contextual files, and validate the setup before launching agents for small, well-scoped features.

How do I monitor and clean up worktree agents during parallel development?

You monitor and clean up worktree agents by using status and log commands to observe progress and recover resources throughout the agent lifecycle.

Do I need trellis Python scripts to initialize parallel worktree agents?

Yes, the orchestration process invokes trellis Python scripts to initialize and monitor worktree agents during parallel development.