using-git-worktrees
Create or verify an isolated git worktree before starting any development work. Prevents main branch contamination, enables parallel feature development, and gives subagents a clean baseline. Use at the start of every feature branch.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 490
01 前言 Front Matter
- name
- using-git-worktrees
- description
- Create or verify an isolated git worktree before starting any development work. Prevents main branch contamination, enables parallel feature development, and gives subagents a clean baseline. Use at the start of every feature branch.
03 SKILL.md 正文
Using Git Worktrees
Why Worktrees
A worktree is a second checkout of the same repo in a separate directory. Each worktree has its own working tree and HEAD, but shares the git object store. This means:
- Subagents work in isolation — no interference with your main session
- You can switch tasks without stashing
- Parallel features develop independently
- Clean rollback: abandon the worktree, nothing pollutes main
When to Use
Use at the START of every feature or bug fix. Do NOT start implementation until a clean worktree exists or you've confirmed you're already in one.
Mandatory before:
subagent-driven-developmentskillexecuting-plansskill- Any work touching more than one file
The Process
Step 1: Detect Existing Isolation
First check — are you already isolated?
# Check if current directory is a worktree (not the main checkout)
git worktree list
pwd
If you're already in a worktree for this feature: proceed to Step 3 (verify clean baseline). If you're in the main checkout: proceed to Step 2.
Step 2: Create the Worktree
# Create worktree + new branch in one command
git worktree add ../worktrees/<feature-name> -b feat/<feature-name>
# Examples:
git worktree add ../worktrees/stripe-billing -b feat/stripe-billing
git worktree add ../worktrees/fix-auth-bug -b fix/auth-token-expiry
The worktree is created at ../worktrees/<feature-name> (sibling of the project root).
If the project uses .claude/worktrees/, use that path instead:
git worktree add .claude/worktrees/<feature-name> -b feat/<feature-name>
Step 3: Verify Clean Baseline
Move into the worktree and confirm it starts clean:
cd ../worktrees/<feature-name> # or .claude/worktrees/<feature-name>
git status # Should show: "nothing to commit"
git log --oneline -3 # Confirm you branched from the right point
If status shows unexpected changes: something is wrong — investigate before proceeding.
Step 4: Run Project Setup
Install dependencies and confirm the baseline builds:
npm install # or pip install -r requirements.txt / go mod download
npm run build # Confirm baseline build passes BEFORE any changes
npm test # Confirm baseline tests pass BEFORE any changes
If baseline build or tests fail: STOP. Fix the issue on main first, then recreate the worktree.
Step 5: Proceed with Work
Now development starts. The worktree is isolated, the baseline is confirmed clean.
Cleanup After Work Completes
After the branch is merged or abandoned:
# From the main checkout (not from inside the worktree)
git worktree remove ../worktrees/<feature-name>
git branch -d feat/<feature-name> # Only after merge
Common Issues
| Issue | Fix |
|---|---|
| "already checked out" error | The branch exists in another worktree — use a different branch name |
| Worktree has unexpected changes | Run git status to investigate; never force-remove with uncommitted work |
| Setup script fails in worktree | Check for absolute paths in scripts; worktrees use different working directories |
| Submodules not initialized | Run git submodule update --init --recursive in the new worktree |
Worktree vs Branch Checkout
git worktree |
git checkout -b |
|
|---|---|---|
| Main session disrupted | No | Yes |
| Parallel work possible | Yes | No |
| Independent node_modules | Yes (separate dir) | Shared |
| Subagent isolation | Clean | Risk of contamination |
Always use worktrees for subagent work. The isolation is the point.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.