Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.
npx skills add https://github.com/GanyuanRan/Aegis --skill using-git-worktrees
A worktree is an exception for simultaneously checking out another Git history,
not a general safety badge. Prefer the current workspace and reuse an existing
suitable worktree. A branch decision and a worktree decision are separate.
Core principle: create only with necessity and ownership evidence; pair every
created worktree with a cleanup path.
Announce at start: explain which concrete checkout conflict requires a
worktree.
Before mutation, record the repository root, HEAD, branch/detached state,
staged/unstaged/untracked paths, active Git operations, and:
git worktree list --porcelain
Stop on detached HEAD, unresolved conflicts, or an active merge/rebase/
cherry-pick/revert/bisect. Preserve user state: no automatic stash, reset,
clean, broad staging, or commit.
Before deciding necessity or placement, read the smallest relevant project
AGENTS.md, CLAUDE.md, current authority, and existing worktree convention.
Repository policy may require or forbid isolation and owns any approved
in-repo location; do not discover that policy after creating the checkout.
Create at most one task-owned worktree only when one of these is true:
Task complexity, planning, TDD, use of subagents, or a main/master branch
name is not sufficient. Same-task subagents share one workspace; do not create
per-subagent or nested worktrees. If independent history is unnecessary, do not
create a branch either.
Record: reason, branch, exact path, creating coordinator, and expected cleanup
event. If the owner or cleanup condition is unknown, stop before creation.
Use an existing repository convention only when the target directory is already
ignored (git check-ignore). Never edit or commit .gitignore solely to host a
worktree. If no safe in-repo convention exists, use a task-specific external
user-level temporary directory outside the repository. Resolve and verify the
exact path before creation; do not target a broad home, workspace, or repo root.
Prefer reusing an existing branch carrying the same goal. Create a branch only
when the approved Git lifecycle requires independent history.
# Existing branch
git worktree add <exact-path> <branch>
# New independently justified branch
git worktree add -b <branch> <exact-path> <start-point>
Read back git worktree list --porcelain, the new worktree's HEAD/branch, and
its status. Do not use force flags.
Read the project's install docs, lockfiles, and existing setup scripts. Run
only setup the project explicitly requires. Do not infer npm install,
cargo build, pip install, poetry install, or dependency downloads merely
from manifest presence.
Run the smallest relevant baseline verification. If setup or tests fail, report
the exact failure and preserve the worktree; do not hide it by mutating unrelated
files.
Report the exact path, branch, start HEAD, baseline result, owner, and cleanup
trigger. The creating coordinator remains responsible until it proves cleanup
or explicitly hands ownership off.
Use finishing-a-development-branch after the task commit or integration
decision. A worktree may usually be removed while its unmerged branch remains;
an open PR does not require a permanent checkout.
Never:
.gitignore merely to make worktree creation possible;Called conditionally by planning/execution workflows only after the necessity
decision. Pairs with finishing-a-development-branch for evidence-led cleanup.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take ganyuanran/using-git-worktrees from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip, npm.
Without those the skill loads but fails at the first command.