agentleFS
jtsang4jtsang4/efficient-coding/skills/worktree-manager/SKILL.md

worktree-manager

Skill2 starsChanged 2 months agoMITView on GitHub

Manage Git worktrees. Use when asked to create/switch/list/merge/remove worktrees, to keep multiple branches in parallel directories, or to clean up worktrees safely during development.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

21 rules. 0 are common, 10 are distinctive, and 11 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 11

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use Worktrunk (wt) as the single interface for Git worktree management: create/switch worktrees, list global status, merge back to the …

    line 10
  2. Very specific:

    Do not preflight-check wt on every invocation.

    line 16
  3. Very specific:

    Ask the user: "I can't run wt because it isn't installed.

    line 18
  4. Distinctive:

    If the user says yes:

    line 19
  5. Very specific:

    Run the installer script: scripts/install_worktrunk.sh

    line 20
  6. Distinctive:

    Do not install shell integration without confirmation (it edits shell rc files):

    line 25
  7. Very specific:

    Ask before running: wt config shell install

    line 26
  8. Very specific:

    Before wt merge / wt remove / anything with --force / -D:

    line 30
  9. Distinctive:

    If the user gave a branch/worktree name:

    line 47
  10. Distinctive:

    If the user asked to create a new branch/worktree:

    line 49
  11. Distinctive:

    Default (this repo): create the worktree by copying the current working state from the current worktree, so experiments are isolated but …

    line 50
  12. Distinctive:

    If the user gave no name:

    line 53
  13. Distinctive:

    Do not invent naming conventions.

    line 57
  14. Very specific:

    If wt switch does not change directories in the current shell, suggest enabling shell integration (with confirmation) via wt config shell …

    line 58
  15. Very specific:

    If the user explicitly wants a completely clean worktree (skip all hooks/copy behavior), pass --no-verify (e.g.

    line 60
  16. Distinctive:

    If the user needs machine-readable output, use the JSON option supported by Worktrunk (if available in their version) and paste only the …

    line 67
  17. Very specific:

    If any flag/target behavior is unclear, check: wt merge --help

    line 75
  18. Distinctive:

    If the user wants to keep the worktree, use the appropriate Worktrunk flag (only if requested) to prevent removal.

    line 77
  19. Very specific:

    Do not run wt merge if the tree is dirty unless the user explicitly tells you to proceed and how to handle changes.

    line 80
  20. Distinctive:

    Only use destructive options if the user explicitly asks:

    line 89
  21. Very specific:

    If flags/behavior are unclear, check: wt remove --help

    line 92

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Worktree Manager

Overview

Use Worktrunk (wt) as the single interface for Git worktree management: create/switch worktrees, list global status, merge back to the default branch, and remove worktrees safely. Prefer safe operations; never use destructive flags unless the user explicitly requests them.

Workflow Decision Tree

Recovery: If a wt command fails because wt is missing

Do not preflight-check wt on every invocation. Instead, attempt the requested wt command. If it fails with an error like "command not found: wt" (or equivalent), then:

  1. Ask the user: "I can't run wt because it isn't installed. Should I install Worktrunk now (recommended)?"
  2. If the user says yes:
    • Run the installer script: scripts/install_worktrunk.sh
      • Example: bash <SKILL_DIR>/scripts/install_worktrunk.sh
    • Verify: wt --version
    • Re-run the original wt ... command.
  3. Do not install shell integration without confirmation (it edits shell rc files):
    • Ask before running: wt config shell install

Step 1: Always run guardrails before merge/remove

Before wt merge / wt remove / anything with --force / -D:

  1. Confirm repo context:
    • git rev-parse --show-toplevel
    • pwd
  2. Confirm working tree cleanliness (if dirty, ask what to do; do not proceed):
    • git status --porcelain
  3. Confirm the current worktree and branch:
    • git branch --show-current
    • wt list (use as the global source of truth for other worktrees)

Step 2: Handle the user request via the matching workflow

A) Create or switch worktrees (most common)

Goal: "Put branch X into its own directory and switch into it."

  1. If the user gave a branch/worktree name:
    • wt switch <name>
  2. If the user asked to create a new branch/worktree:
    • Default (this repo): create the worktree by copying the current working state from the current worktree, so experiments are isolated but start "warm" (deps + uncommitted changes).
    • Implement with Worktrunk by creating from the current worktree as the base (use --base=@ unless the user explicitly wants a clean base).
    • Run: wt switch --create <name> --base=@
  3. If the user gave no name:
    • Show options with wt list and ask which one to switch to.

Notes:

  • Do not invent naming conventions; follow the repo's existing pattern (or ask).
  • If wt switch does not change directories in the current shell, suggest enabling shell integration (with confirmation) via wt config shell install.
  • This repo has Worktrunk hooks in .config/wt.toml (notably post-create) that may copy the base worktree's working directory into a new worktree.
  • If the user explicitly wants a completely clean worktree (skip all hooks/copy behavior), pass --no-verify (e.g. wt switch --create <name> --base=@ --no-verify).

B) List and diagnose global worktree state

Goal: "What worktrees exist and which ones are dirty/out-of-date?"

  1. wt list
  2. If the user needs machine-readable output, use the JSON option supported by Worktrunk (if available in their version) and paste only the relevant fields.

C) Merge the current worktree branch back and clean up

Goal: "Finish this branch and get back to the default branch cleanly."

  1. Run guardrails (Step 1).
  2. Confirm intent (quickly): target branch is the default branch; merge strategy is Worktrunk defaults unless the user asked otherwise.
  3. If any flag/target behavior is unclear, check: wt merge --help
  4. Run: wt merge
  5. If the user wants to keep the worktree, use the appropriate Worktrunk flag (only if requested) to prevent removal.

Rules:

  • Do not run wt merge if the tree is dirty unless the user explicitly tells you to proceed and how to handle changes.

D) Remove worktrees safely

Goal: "Delete a worktree directory safely without losing uncommitted work."

  1. Run guardrails (Step 1).
  2. Prefer safe removal:
    • wt remove <name>
  3. Only use destructive options if the user explicitly asks:
    • --force (can discard untracked files depending on tool behavior)
    • -D (force-delete an unmerged branch/worktree)
  4. If flags/behavior are unclear, check: wt remove --help

Installation Notes (read only when needed)

See references/install.md for platform-specific notes. Use scripts/install_worktrunk.sh to install after the user confirms.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.