home/dot_agents/skills/create-worktree/SKILL.md
Create a new git worktree using the Worktrunk CLI `wt`. Use this skill when the user asks to create a worktree, set up a new branch in a worktree, says "new worktree", "create worktree", "work on X in a separate worktree", or anything related to creating or initializing git worktrees.
npx skillsauth add deferred/dotfiles create-worktreeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use the Worktrunk CLI wt to create a new worktree with a fresh branch.
Ask for a branch name if the user did not provide one.
Fetch the latest:
git fetch origin
Create the worktree:
wt switch --create <branch-name> --base origin/HEAD --yes --no-cd
Critical: wt switch cannot change the agent's working directory. Parse the worktree path from
the command output and use it as workdir for all subsequent bash commands if the agent needs to
work in the new worktree.
Confirm: report the created branch and worktree path back to the user.
testing
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
tools
Remove git worktrees using the Worktrunk CLI `wt`. Use this skill when the user asks to "remove a worktree", "delete a worktree", "clean up a worktree", "remove branch worktree", or wants to get rid of a parallel development environment. Also trigger when the user mentions removing or deleting worktrees in any form.
testing
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
development
Write and revise Markdown so it is clean, scannable, and consistent. Use this skill whenever you are about to produce Markdown of any kind, including READMEs, docs, guides, notes, reports, issue bodies, pull request text, or comments, even if the user did not explicitly ask for Markdown formatting.