workstream

Create, switch, list, and archive workstreams with isolated pipeline-state directories.

1|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/paulingham/.claude --skill workstream
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: workstream
Source: https://github.com/paulingham/.claude/tree/main/skills/workstream
Command: npx skills add https://github.com/paulingham/.claude --skill workstream

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Teams working on multiple features in parallel often collide over pipeline state, branch naming, and context switching. This Skill provides isolated workstreams with per-workstream state, so contributors can develop concurrently without interfering with each other.

Core Features & Use Cases

  • Create, switch, list, and archive workstreams with independent state directories
  • Enforce branch-prefix conventions (e.g., feat/{name}/) per workstream to avoid collisions
  • Seamless context switching and lifecycle management across active pipelines
  • Integration with the pipeline system to store per-workstream state, builds, and logs

Quick Start

Create a new workstream named my-feature and switch into it to begin using its isolated pipelines.

Frequently Asked Questions about workstream

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

FAQPage Schema
How do I manage parallel feature development without context switching collisions?

Switch between active workstreams to manage parallel feature development without losing pipeline state. The skill persists metadata for each stream, enabling seamless context switching across active pipelines.

How do I enforce branch naming conventions for concurrent feature development?

Archive completed workstreams to clean up active feature development pipelines. Archiving updates the workstream status while preserving its isolated state directories and metadata for future reference.

How do I list active workstreams and switch contexts during parallel workflow?

Isolated pipeline-state directories prevent context switching collisions by storing per-workstream state, builds, and logs independently. This ensures contributors can develop concurrently without overwriting each other's pipeline data.

Does this parallel workflow tool store per-workstream builds and logs?

Create a new workstream and switch into it to begin using isolated pipelines for parallel feature development. This immediately establishes an independent state directory and applies branch-prefix conventions for that stream.