Shep Workstreams

Shep Workstreams is an AI Engineering skill for Claude Code, published by shep-ai in shep.

247 stars53 forkson shep-ai/shepAdded 2026/09/02Repository updated 2026/08/28

agent-orchestrationagentic-aiaiai-agentsai-code-generationai-codingai-nativeautomationclaudeclaude-codeclicursordeveloper-toolsdevtoolsgeminigit-worktreesparallel-developmentsdlctypescriptworktrees

Install in seconds

Install Shep Workstreams

Copy Shep Workstreams into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/shep-ai/shep/tree/main/.claude/skills/shep-workstreams ~/.claude/skills/shep-workstreams

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/shep-ai/shep.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/shep-workstreams/SKILL.md in shep-ai/shep
Installs to: ~/.claude/skills/shep-workstreams
Collection: One of 19 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Shep Workstreams does

Shep Workstreams breaks a large body of work into parallel workstreams, then drives shep CLI execution wave by wave. Use it when planning docs, roadmaps, or epics need to be turned into isolated features with clear dependencies.

Shep Workstreams is cataloged under AI Engineering on DirSkills. Shep Workstreams comes from a repository tagged agent-orchestration, agentic-ai, ai, ai-agents and ai-code-generation.

Documentation

README

Excerpt

Workstream Breakdown & Parallel Execution with Shep

Turn a large, vague body of work into a small set of parallel workstreams, then execute each one as an isolated shep feature. One workstream = one feature = one worktree = one agent.

The rule this skill exists to enforce

Never tell an agent "work on all of it." That produces context loss, jumping between unrelated tasks, dozens of touched files, giant commits, and merge conflicts.

Act like a tech lead: partition first, then run one focused agent per partition.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Shep Workstreams

What else does shep-ai publish alongside Shep Workstreams?
Shep Workstreams is one of 19 skills that DirSkills catalogs from shep-ai/shep, the repository it ships in. Its siblings there include Architecture Reviewer, Commit PR and Cross-Validate Artifacts. Each one is a separate skill with its own page in this directory, installs the same way Shep Workstreams does, and is maintained by shep-ai in that same repository. The rest of the collection is listed on the shep-ai/shep page.
How does Shep Workstreams compare to other AI Engineering skills?
Shep Workstreams ranks #2359 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Shep Workstreams against them. Open each page to compare what they document and how they install.