Agent skill
managing-context-worktree
Evaluates context similarity between new and existing work, automatically creating git worktree on a new branch when tasks differ. Activates on task start, new feature implementation, or switching to different issues.
Install this agent skill to your Project
npx add-skill https://github.com/jiunbae/agent-skills/tree/main/development/context-worktree
SKILL.md
Context Worktree
Auto-separate unrelated work into git worktrees.
When to Activate
- Starting new feature while another is in progress
- Switching to different issue/task
- Requested work differs from current branch context
Workflow
Step 1: Evaluate Similarity
Compare new request against current branch:
- File paths involved
- Feature/module overlap
- Related issues/PRs
Similar: Continue on current branch Different: Create new worktree
Step 2: Create Worktree (if different)
# Create worktree with new branch
git worktree add ../project-feature feature/new-feature
# Switch to worktree
cd ../project-feature
Step 3: Work in Isolation
- Changes in worktree don't affect main workspace
- Can switch back anytime:
cd ../project-main
Commands
# List worktrees
git worktree list
# Add worktree
git worktree add <path> <branch>
# Remove worktree
git worktree remove <path>
# Prune stale worktrees
git worktree prune
Decision Matrix
| Current Work | New Request | Action |
|---|---|---|
| Feature A | Bug in Feature A | Continue |
| Feature A | Feature B | New worktree |
| Feature A | Hotfix | New worktree |
| None | Any | Continue |
Best Practices
DO:
- Use descriptive worktree paths:
../project-{feature} - Clean up finished worktrees
DON'T:
- Create worktree for tiny tasks
- Forget to push before removing worktree
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
implementing-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel implementation in the background. Separates independent tasks from planning docs, each agent writes code directly. Context-safe with auto-save. Use for "백그라운드 구현", "bg impl", "병렬 구현", "Codex로 구현", "구현해줘", "코드 작성해줘" requests.
review-fix-loop
Autonomous review-fix cycle that continuously reviews code using background-reviewer, fixes issues, and repeats until all findings are resolved. Use for "리뷰 루프", "자동 개선", "review fix loop", "리뷰 반복", "코드 개선 루프", "keep reviewing" requests.
planning-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel planning in the background with auto-save. Agents continue running even when session hits context limits. Use for "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", "기획해줘", "N명이 기획", "계획", "플래닝", "plan", "설계" requests.
background-reviewer
Orchestrates multi-LLM parallel code review using Claude, Codex, and Gemini. Each agent reviews from a different perspective using agent personas (security, architecture, code quality, performance). Supports persona-based review via `agt persona review`. Use for "코드 리뷰", "리뷰해줘", "bg review", "멀티 리뷰", "background review", "페르소나 리뷰" requests.
managing-context
Discovers and loads relevant project context from markdown documentation before each task. Matches context documents based on keywords, file paths, and task types. Use at task start to access project plans, architecture, and implementation status.
indexing-static-context
Provides an index of global static context files in ~/.agents/. Returns appropriate static file paths for natural language queries like "내 정보", "보안 규칙". Use when other skills or agents need to locate reference information.
Didn't find tool you were looking for?