Using Git Worktrees logo

Using Git Worktrees

Community
aaddrick
using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees in .worktrees/

Overview

Publisheraaddrick
Repositoryclaude-pipeline
Skill nameusing-git-worktrees
Stars
130
Forks
17
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by aaddrick on GitHub. Read the source before you install it.

Installation

Install the Using Git Worktrees AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aaddrick/claude-pipeline/tree/main/.claude/skills/using-git-worktrees
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aaddrick/claude-pipeline.git /tmp/claude-pipeline
mkdir -p .claude/skills
cp -r /tmp/claude-pipeline/.claude/skills/using-git-worktrees .claude/skills/using-git-worktrees
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Using Git Worktrees in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Using Git Worktrees on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Using Git Worktrees is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Using Git Worktrees

Overview

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

Location: Always use .worktrees/ (per CLAUDE.md)

Announce at start: "I'm using the using-git-worktrees skill to set up an isolated workspace."

Safety Verification

Verify .worktrees/ is ignored before creating worktree:

bash
git check-ignore -q .worktrees 2>/dev/null

If NOT ignored: Add to .gitignore and commit before proceeding.

Why critical: Prevents accidentally committing worktree contents to repository.

Creation Steps

1. Create Worktree

bash
git worktree add .worktrees/$BRANCH_NAME -b $BRANCH_NAME $BASE_BRANCH
cd .worktrees/$BRANCH_NAME

2. Run Project Setup

Laravel:

Fresh worktrees don't have vendor/ or node_modules/. Install dependencies first:

bash
# 1. Create bootstrap/cache (required for composer)
mkdir -p bootstrap/cache

# 2. Install PHP dependencies
composer install --no-interaction

# 3. Run Laravel setup (migrations, seeds, caches)
php artisan migrate --seed

# 4. Build frontend assets (Vite manifest required for tests)
npm install && npm run build

Why this order matters:

  • bootstrap/cache must exist before composer runs post-install scripts
  • vendor/ must exist before artisan commands work
  • Vite manifest must exist or tests using views will fail

Other projects: Auto-detect from project files:

bash
if [ -f package.json ]; then npm install; fi
if [ -f Cargo.toml ]; then cargo build; fi
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f pyproject.toml ]; then poetry install; fi
if [ -f go.mod ]; then go mod download; fi

3. Verify Baseline

Run tests to ensure worktree starts clean:

bash
# Laravel
php artisan test

# Other
npm test / cargo test / pytest / go test ./...

If tests fail: Verify setup completed correctly (vendor/, node_modules/, Vite manifest all exist). Compare with main worktree to identify if failures are pre-existing.

If tests pass: Report ready.

4. Report Location

Worktree ready at <full-path>
Branch: <branch-name>
Tests: <N> passed (<M> pre-existing failures if any)
Ready to implement <feature-name>

Quick Reference

SituationAction
Creating worktreegit worktree add .worktrees/$BRANCH -b $BRANCH $BASE
.worktrees/ not ignoredAdd to .gitignore + commit first
Laravel projectmkdir -p bootstrap/cache → composer install → php artisan migrate --seed → npm install && npm run build
Other projectsAuto-detect from package.json, Cargo.toml, etc.
Tests fail during baselineVerify setup complete (vendor/, node_modules/, Vite manifest), compare with main

Common Mistakes

Skipping ignore verification

  • Problem: Worktree contents get tracked, pollute git status
  • Fix: Always use git check-ignore before creating worktree

Running artisan commands before composer install

  • Problem: Fresh worktrees have no vendor/ directory - artisan commands fail
  • Fix: Run composer install first, then artisan commands

Missing bootstrap/cache directory

  • Problem: Composer post-install scripts fail with "directory must be present and writable"
  • Fix: Create mkdir -p bootstrap/cache before running composer install

Skipping npm build

  • Problem: Tests that render views fail with "Vite manifest not found"
  • Fix: Run npm install && npm run build after Laravel setup

Hardcoding setup commands

  • Problem: Breaks on projects using different tools
  • Fix: Use documented sequence for Laravel, auto-detect for others

Example Workflow

You: I'm using the using-git-worktrees skill to set up an isolated workspace.

[Verify ignored: git check-ignore .worktrees - confirmed]
[Create worktree: git worktree add .worktrees/issue-123 -b issue-123-feature aw-next]
[mkdir -p bootstrap/cache]
[composer install --no-interaction]
[php artisan migrate --seed]
[npm install && npm run build]
[php artisan test - all tests passed]

Worktree ready at /home/user/project/.worktrees/issue-123
Branch: issue-123-feature
Tests: 639 passed (0 failures)
Ready to implement feature

Red Flags

Never:

  • Create worktree without verifying .worktrees/ is ignored
  • Run artisan commands before composer install in fresh worktree
  • Skip npm run build - tests will fail on missing Vite manifest

Always:

  • Use .worktrees/ directory
  • Verify directory is ignored
  • Create bootstrap/cache before composer install
  • Follow setup order: composer → artisan migrate → npm build

Integration

Called by:

  • brainstorming (Phase 4) - when design is approved
  • implement-issue - for isolated feature work

Pairs with:

  • finishing-a-development-branch - cleanup after work complete
  • subagent-driven-development - work happens in this worktree

Frequently asked questions

What does the Using Git Worktrees AI skill do?

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees in .worktrees/

Why use Using Git Worktrees on TypingMind?

Because you install it once and use it with any model. Using Git Worktrees is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Using Git Worktrees in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aaddrick/claude-pipeline/tree/main/.claude/skills/using-git-worktrees. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Using Git Worktrees?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Using Git Worktrees?

As many as you like. As long as a model supports skills, you can use Using Git Worktrees with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Using Git Worktrees AI skill free?

Yes. It is published on GitHub by aaddrick under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇