Menu
Manage git worktrees for parallel development workflows — create, sync, and spotlight preview.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Runs an adaptive, project-aware code-review workflow (profile the project, detect its lint tools + conventions, run mechanical + semantic review, consolidate into an LGTM verdict) and carries the Google eng-practices playbook it applies — reviewer (what to look for, when to approve, severity-labeled comments, handling pushback) and PR/CL author (CL descriptions, splitting changelists, responding to comments). Use when reviewing or authoring a PR/MR/CL/diff, running a code review, deciding LGTM or LGTM threshold, authoring a merge request, assessing code health, handling a hotfix review, or replying to review feedback.
Push books/docs and read notes from an Onyx BOOX e-reader account (push.boox.com / send2boox.com) WITHOUT the web UI, via the self-contained `boox.mjs` CLI. Uploads a file to Aliyun OSS, writes a digital_content doc into the device's MESSAGE sync channel, and calls saveAndPush to notify the device — the exact 3-step flow the web app performs. Also lists the push list, lists synced notes, removes pushed items, and shows device online status. Auth = long-lived JWT via BOOX_TOKEN env or a token file.
Capture this session's repeatable process into a reusable SKILL.md file via guided interview.
Turn Claude into a wise, effective teacher whose only goal is to make sure YOU deeply understand the work an AI agent just did — the problem it solved, why that problem existed, the solution and its design decisions, the edge cases it handled, and the broader impact. Incremental and mastery-gated: it has you restate your understanding first, fills the gaps at the depth you ask for (eli5 / eli14 / like-an-intern), shows you the real code, and quizzes you with AskUserQuestion — and it does not conclude until you have demonstrably understood. Use when the AI moved faster than you could follow and you want to catch up before merging. Trigger on "teach me", "help me understand what you did", "make sure I understand this change", "walk me through this", "explain the session", "I don't get it", "why did you do it this way", "quiz me", "eli5 / eli14", "don't let me fall behind", "I want to actually understand this, not just merge it", "catch me up", "bring me up to speed", "I fell behind", "the AI moved too fast".
Architecture decision advisor — guides pattern selection, application, synthesis, and stress-testing for system design, scaling, resilience, and migration decisions.
Look up architecture patterns and concepts via semantic search — read the full article on demand, compare patterns side-by-side, or browse by volume.
| name | aio-worktree |
| description | Manage git worktrees for parallel development workflows — create, sync, and spotlight preview. |
| when_to_use | create worktree, sync worktree, manage worktrees, parallel development, worktree, git worktree, branch isolation, spotlight, worktree merge, worktree cleanup |
| effort | medium |
| argument-hint | <branch-name> |
Manages git worktrees for parallel development workflows.
which git 2>/dev/null || echo "NOT INSTALLED"echo "${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"WT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
Set this in every shell block that calls a script. Then reference scripts as $WT/script-name.
| Script | Purpose |
|---|---|
worktree-create.sh | Create new worktree with branch |
worktree-list.sh | List all worktrees and their status |
worktree-sync.sh | Sync worktree ↔ main (rebase + ff) |
worktree-spotlight.sh | Live file sync for hot reload |
worktree-spotlight-status.sh | Check if spotlight is running |
worktree-merge.sh | Merge worktree branch to/from parent |
worktree-remove.sh | Remove worktree and delete branch |
worktree-cleanup.sh | Emergency cleanup after crash |
WT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
$WT/worktree-create.sh <name> [source_ref]
# Examples:
$WT/worktree-create.sh feature-login # from HEAD
$WT/worktree-create.sh hotfix-bug main # from main branch
$WT/worktree-create.sh experiment abc123 # from specific commit
# Creates:
# Folder: {repo}--wtr-{name} (e.g., myrepo--wtr-feature-login)
# Branch: wtr-{name} (e.g., wtr-feature-login)
Sync worktree with parent branch. Both end up at the same commit with same hash.
# From within worktree directory
$WT/worktree-sync.sh
How it works:
Result: Both branches at same commit, same hash. No duplicates.
Example workflow:
# In worktree: make changes, commit
git add . && git commit -m "feat: new feature"
# Sync with main
$WT/worktree-sync.sh
# Output:
# Syncing: wtr-feature ↔ main
# Status: worktree +2 commits, parent +1 commits
# === Step 1: Rebase onto main ===
# === Step 2: Fast-forward main ===
# Sync complete!
# Both branches at: abc1234
Preview worktree changes in main repo with hot reload. One-way sync, temporary.
# Run in background from MAIN repo
$WT/worktree-spotlight.sh <worktree_path> . [excludes...]
# Example:
$WT/worktree-spotlight.sh ../myrepo--wtr-feature . node_modules dist .env
How it works:
Important:
run_in_background: trueTo stop: Ctrl+C or kill <PID>. Cleanup is automatic.
WT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
$WT/worktree-remove.sh <path_or_name>
# Examples:
$WT/worktree-remove.sh ../myrepo--wtr-feature # by path
$WT/worktree-remove.sh feature # by name (auto-resolves path)
WT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
# Agent A creates worktree
$WT/worktree-create.sh agent-a-task
# Agent B creates worktree
$WT/worktree-create.sh agent-b-task
# Both work and commit independently...
# Agent A syncs first
cd ../repo--wtr-agent-a-task
$WT/worktree-sync.sh
# main now has Agent A's commits
# Agent B syncs (gets A's work + pushes B's work)
cd ../repo--wtr-agent-b-task
$WT/worktree-sync.sh
# main now has both A and B's commits
# Agent B's worktree also has A's commits
# Agent A syncs again to get B's work
cd ../repo--wtr-agent-a-task
$WT/worktree-sync.sh
# All three (main, worktree-a, worktree-b) now identical
worktree-spotlight.sh <worktree> . node_modulesworktree-sync.shworktree-create.sh feature-xworktree-sync.shworktree-remove.sh feature-xWT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
$WT/worktree-cleanup.sh .
Script will stop at rebase conflict. Resolve conflicts, then:
git rebase --continue
# Then run sync again
$WT/worktree-sync.sh
When using Agent Teams (experimental, requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1), combine worktrees with agent teams for maximum parallel safety.
Pattern: Each teammate gets their own worktree
WT="${CLAUDE_PLUGIN_ROOT}/skills/aio-worktree"
# Lead creates worktrees for each teammate
$WT/worktree-create.sh teammate-frontend
$WT/worktree-create.sh teammate-backend
$WT/worktree-create.sh teammate-tests
# Each teammate works in their own worktree (no file conflicts)
# Teammate messages via SendMessage when ready to sync
# Lead coordinates sync order to avoid conflicts
Why: Agent teams let multiple Claude instances work in parallel. Worktrees give each instance an isolated filesystem. Combined = true parallel development without merge conflicts.
Sync strategy with teams:
worktree-sync.sh in order (first-done-first-synced)When NOT to combine: If tasks are small and touch different files anyway, agent teams alone (without worktrees) work fine. Use worktrees when there's ANY risk of file overlap.
wtr- prefix for easy identification
{repo}--wtr-{name} (e.g., myrepo--wtr-feature)wtr-{name} (e.g., wtr-feature)brew install fswatch)