メニュー
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when executing implementation plans with independent tasks in the current session
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when you have a spec or requirements for a multi-step task, before touching code
Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons
Use when you want to evolve your own capabilities — create new tools to avoid repeating patterns, add hooks to improve your own behavior, build skills to accumulate domain knowledge, or override built-in tools to adapt to project needs. This is your self-iteration interface.
| name | compose:worktree |
| hidden | true |
| description | Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback |
Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools. Fall back to manual git worktrees only when no native tool is available.
Core principle: Detect existing isolation first. Then use native tools. Then fall back to git. Never fight the harness.
Announce at start: "I'm using the compose:worktree skill to set up an isolated workspace."
Before creating anything, check if you are already in an isolated workspace.
GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
BRANCH=$(git branch --show-current)
Submodule guard: GIT_DIR != GIT_COMMON is also true inside git submodules. Before concluding "already in a worktree," verify you are not in a submodule:
# If this returns a path, you're in a submodule, not a worktree — treat as normal repo
git rev-parse --show-superproject-working-tree 2>/dev/null
If GIT_DIR != GIT_COMMON (and not a submodule): You are already in a linked worktree. Skip to Step 3 (Project Setup). Do NOT create another worktree.
Report with branch state:
<path> on branch <name>."<path> (detached HEAD, externally managed). Branch creation needed at finish time."If GIT_DIR == GIT_COMMON (or in a submodule): You are in a normal repo checkout.
Check memory for a worktree-consent preference in the compose-preferences memory file, or check your instructions for a declared worktree preference. If either exists, honor it silently.
If no saved preference, use compose:ask:
WorktreeSet up an isolated worktree? It protects your current branch from changes.Yes (Recommended), description: Create an isolated worktree for this workNo, description: Work directly on the current branchAlways use worktrees, description: Use worktrees now and remember for future sessionsNever use worktrees, description: Work in place now and remember for future sessionsIf no user is available, create the worktree and proceed.
If "Always" or "Never": Save to the compose-preferences memory file as worktree-consent: always or worktree-consent: never.
If the user declined (chose "No" or "Never"), work in place and skip to Step 3.
You have two mechanisms. Try them in this order.
The user has asked for an isolated workspace (Step 0 consent). Do you already have a way to create a worktree? It might be a tool with a name like EnterWorktree, WorktreeCreate, a /worktree command, or a --worktree flag. If you do, use it and skip to Step 3.
Native tools handle directory placement, branch creation, and cleanup automatically. Using git worktree add when you have a native tool creates phantom state your harness can't see or manage.
Only proceed to Step 1b if you have no native worktree tool available.
Only use this if Step 1a does not apply — you have no native worktree tool available. Create a worktree manually using git.
Follow this priority order. Explicit user preference always beats observed filesystem state.
Check your instructions for a declared worktree directory preference. If the user has already specified one, use it without asking.
Check for an existing project-local worktree directory:
ls -d .worktrees 2>/dev/null # Preferred (hidden)
ls -d worktrees 2>/dev/null # Alternative
If found, use it. If both exist, .worktrees wins.
Check for an existing global directory:
project=$(basename "$(git rev-parse --show-toplevel)")
ls -d ~/.config/compose/worktrees/$project 2>/dev/null
If found, use it (backward compatibility with legacy global path).
If there is no other guidance available, default to .worktrees/ at the project root.
MUST verify directory is ignored before creating worktree:
git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null
If NOT ignored: Add to .gitignore, commit the change, then proceed.
Why critical: Prevents accidentally committing worktree contents to repository.
Global directories (~/.config/compose/worktrees/) need no verification.
project=$(basename "$(git rev-parse --show-toplevel)")
# Determine path based on chosen location
# For project-local: path="$LOCATION/$BRANCH_NAME"
# For global: path="~/.config/compose/worktrees/$project/$BRANCH_NAME"
git worktree add "$path" -b "$BRANCH_NAME"
cd "$path"
Sandbox fallback: If git worktree add fails with a permission error (sandbox denial), tell the user the sandbox blocked worktree creation and you're working in the current directory instead. Then run setup and baseline tests in place.
Auto-detect and run appropriate setup:
# Node.js
if [ -f package.json ]; then npm install; fi
# Rust
if [ -f Cargo.toml ]; then cargo build; fi
# Python
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f pyproject.toml ]; then poetry install; fi
# Go
if [ -f go.mod ]; then go mod download; fi
Run tests to ensure workspace starts clean:
# Use project-appropriate command
npm test / cargo test / pytest / go test ./...
If tests fail: Report failures, then use compose:ask:
Baseline TestsBaseline tests have <N> failures (pre-existing, not caused by your changes).Proceed anyway (Recommended), description: Start working — failures existed before this branchInvestigate first, description: Debug test failures before startingIf no user is available, proceed with the failing tests.
If tests pass: Report ready.
Worktree ready at <full-path>
Tests passing (<N> tests, 0 failures)
Ready to implement <feature-name>
| Situation | Action |
|---|---|
| Already in linked worktree | Skip creation (Step 0) |
| In a submodule | Treat as normal repo (Step 0 guard) |
| Native worktree tool available | Use it (Step 1a) |
| No native tool | Git worktree fallback (Step 1b) |
.worktrees/ exists | Use it (verify ignored) |
worktrees/ exists | Use it (verify ignored) |
| Both exist | Use .worktrees/ |
| Neither exists | Check instruction file, then default .worktrees/ |
| Global path exists | Use it (backward compat) |
| Directory not ignored | Add to .gitignore + commit |
| Permission error on create | Sandbox fallback, work in place |
| Tests fail during baseline | Report failures + ask |
| No package.json/Cargo.toml | Skip dependency install |
git worktree add when the platform already provides isolationgit check-ignore before creating project-local worktreeNever:
git worktree add when you have a native worktree tool (e.g., EnterWorktree). This is the #1 mistake — if you have it, use it.Always: