parallel-worktrees
Parallel Worktrees creates isolated git working copies to enable simultaneous development across multiple branches without interrupting long-running processes. Use this skill when waiting on tests or builds, exploring multiple implementation approaches concurrently, or needing to context-switch between feature development and bug fixes while maintaining separate, interference-free working directories in each session.
git clone --depth 1 https://github.com/rohitg00/pro-workflow /tmp/parallel-worktrees && cp -r /tmp/parallel-worktrees/skills/parallel-worktrees ~/.claude/skills/parallel-worktreesSKILL.md
# Parallel Worktrees Zero dead time. While one session runs tests, work on something else. ## Trigger Use when waiting on tests, long builds, exploring approaches, or needing to review and develop simultaneously. ## Quick Start **Claude Code:** ```bash claude --worktree # or claude -w (auto-creates isolated worktree) ``` **Cursor / Any editor:** ```bash git worktree add ../project-feat feature-branch # Open the new worktree folder in a second editor window ``` Both approaches create an isolated working copy where changes don't interfere with your main session. ## Claude Code Extras These features are Claude Code-specific (skip if using Cursor): - `claude -w` auto-creates and cleans up worktrees - Subagents support `isolation: worktree` in agent frontmatter - `Ctrl+F` kills all background agents (two-press confirmation) - `Ctrl+B` sends a task to background ## Workflow 1. Show current worktrees: `git worktree list` 2. Create a worktree for the parallel task. 3. Open a new editor/terminal session in the worktree. 4. When done, clean up the worktree. ## Commands ```bash git worktree list git worktree add ../project-feat feature-branch git worktree add ../project-fix bugfix-branch git worktree add ../project-exp -b experiment git worktree remove ../project-feat git worktree prune ``` ## Usage Pattern ``` Terminal 1: ~/project → Main work Terminal 2: ~/project-feat → Feature development Terminal 3: ~/project-fix → Bug fixes ``` Each worktree runs its own AI session independently. ## When to Parallelize | Scenario | Action | |----------|--------| | Tests running (2+ min) | Start new feature in worktree | | Long build | Debug issue in parallel | | Exploring approaches | Compare 2-3 simultaneously | | Review + new work | Reviewer in one, dev in other | | Waiting on CI | Start next task in worktree | ## Guardrails - Each worktree is a full working copy — changes are isolated. - Before removing a worktree, verify changes are committed: `git -C ../project-feat status` - Don't forget to clean up worktrees when done (`git worktree prune`). - Avoid editing the same files in multiple worktrees simultaneously. ## Output - Current worktree list - Created worktree path and branch - Instructions for opening a new session
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.