parallel-dev

Dispatch multiple agents into isolated worktrees to implement GitHub issues with TDD.

5|1|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/blamechris/chroxy --skill parallel-dev-blamechris
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-dev
Source: https://github.com/blamechris/chroxy/tree/main/.claude/skills/parallel-dev
Command: npx skills add https://github.com/blamechris/chroxy --skill parallel-dev-blamechris

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel autonomous development sessions by dispatching multiple agents into isolated worktrees to implement GitHub issues with TDD, avoiding branch conflicts and manual coordination.

Core Features & Use Cases

  • Orchestrates multiple autonomous agents in isolated worktrees to tackle GitHub issues in parallel.
  • Phase-driven execution with clear phases: queue setup, prompt building, fan-out, result collection, sequential review, and session summary.
  • Auto-decomposition of high-complexity issues into 2-5 sub-issues and batch processing with a hard cap of 10 issues.
  • Provides an idempotent resume strategy based on GitHub state to avoid duplicating work and support interruptions.

Quick Start

Approve the initial queue and let the system autonomously manage decomposition, dispatch, and review across worktrees.

Frequently Asked Questions about parallel-dev

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

FAQPage Schema
How do I run parallel autonomous development sessions on GitHub issues?

Parallel autonomous development on GitHub issues is orchestrated by dispatching multiple agents into isolated worktrees. This approach implements issues using TDD while avoiding branch conflicts and manual coordination across concurrent development tasks.

How does TDD work with parallel agents in isolated worktrees?

TDD with parallel agents works by fanning out isolated agents into separate git worktrees to implement GitHub issues. Each agent independently drives test-driven development phases, gathering structured results for sequential review without branch conflicts.

Can I auto-decompose complex GitHub issues for batch processing?

High-complexity GitHub issues are auto-decomposed into 2-5 sub-issues for batch processing. The orchestration system applies a hard cap of 10 issues maximum to manage parallel agent dispatch and ensure structured sequential review.

What is the best way to resume interrupted parallel development worktrees?

Interrupted parallel development worktrees are resumed using an idempotent strategy based on GitHub state. This prevents duplicating work by checking existing repository state before dispatching agents, safely supporting interruptions and restarts.

Does parallel development orchestration support milestone and label filtering for GitHub issues?

Parallel development orchestration supports sourcing GitHub issues with optional labeling and milestone filtering. This allows auto-detection to select specific issues for parallel work based on repository tags and milestone assignments.

What are the limitations of dispatching multiple agents for parallel TDD?

Dispatching multiple agents for parallel TDD is limited to a hard cap of 10 issues per batch. Complex issues are automatically decomposed into 2-5 sub-issues, and sequential review is required after parallel fan-out to ensure safety constraints.