batch

Run parallel ship pipelines on leased worktrees and integrate branches into one PR.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Jeqqe/jersal-project-template --skill batch-jeqqe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: batch
Source: https://github.com/Jeqqe/jersal-project-template/tree/main/.pi/skills/batch
Command: npx skills add https://github.com/Jeqqe/jersal-project-template --skill batch-jeqqe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the bottleneck of handling multiple GitHub issues sequentially by running each issue’s work in parallel and then combining the results into one integration pull request.

Core Features & Use Cases

  • Parallel ship execution with leased worktrees: Runs multiple ship runs concurrently using a persistent pool of instances for isolation and speed.
  • Dependency-aware fan-out / fan-in: Detects dependency cycles, validates in-batch dependencies, and schedules dependent issues after their prerequisites complete.
  • Single integration PR with issue closure: Once all issue branches are ready, it runs integrate to merge the set into one shippable PR and close the issues.

Quick Start

Run /skill:batch <issue-numbers> to process a partitioned set of issues concurrently (max 4 by default), then create a single integration PR that closes them.

Frequently Asked Questions about batch

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

FAQPage Schema
How do I process multiple GitHub issues in parallel and merge them into one pull request?

You can process multiple GitHub issues in parallel by fanning out ship pipelines across leased worktree instances, then integrate the resulting branches into one consolidated PR that closes all issues.

What is the best way to handle issue dependencies when running parallel CI pipelines?

Handling issue dependencies in parallel CI pipelines requires validating explicit dependency declarations, detecting cycles, and scheduling dependent issues to run only after their prerequisites report READY.

How do I run isolated background sub-agents for concurrent GitHub issue resolution?

Running isolated background sub-agents for concurrent GitHub issue resolution involves leasing separate worktree instances from a persistent pool, spawning tasks in parallel, and resetting instances upon completion.

Can I integrate multiple feature branches into a single shippable PR after parallel execution?

Yes, you can integrate multiple feature branches into a single shippable PR by waiting for all parallel branches to report READY, then invoking an integrate command to merge the set and close the issues.

How do dependency cycles affect parallel GitHub issue processing?

Dependency cycles block parallel GitHub issue processing because the system validates in-batch dependencies and schedules dependent issues only after prerequisites complete, preventing circular execution.

Do I need to manually claim GitHub issues before starting parallel ship execution?

Yes, you must claim GitHub issues before starting parallel ship execution, as the workflow requires claiming issues, validating dependency constraints, and leasing pool instances prior to spawning sub-agents.