agentsclimarketplace

Worktrunk

Skill kpatryk/skills/skills/worktrunk

AI skills

Install
npx -y skills add kpatryk/skills --skill worktrunk

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Expert guide for Worktrunk (the `wt` CLI), a git worktree manager designed for running AI agents in parallel. Invoke this skill whenever a user mentions worktrunk or wt commands (wt switch, wt list, wt merge, wt remove, wt hook, wt step, wt config), asks about git worktrees for AI agents or parallel development, wants to configure LLM commit messages, set up worktree lifecycle hooks, run multiple Claude or Codex agents simultaneously, use wt list CI status, configure the interactive picker, copy build caches between worktrees, or troubleshoot shell integration. Also use for questions about .config/wt.toml, ~/.config/worktrunk/config.toml, hash_port, sanitize filters, wt merge squash/rebase workflow, wt step copy-ignored, wt step prune, agent handoffs, dev servers per worktree, bare repository layouts, or any other worktrunk topic.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

9.8 KB, ~2.2k tokens by cl100k_base, as published. Nobody here has run it

Worktrunk

Help users work with Worktrunk, a CLI tool for managing git worktrees.

Available Documentation

Reference files are synced from worktrunk.dev documentation:

  • references/config.md: User and project configuration (LLM, hooks, command defaults)
  • references/hook.md: Hook types, timing, and execution order
  • references/switch.md, merge.md, list.md, etc.: Command documentation
  • references/llm-commits.md: LLM commit message generation
  • references/tips-patterns.md: Language-specific tips and patterns
  • references/shell-integration.md: Shell integration debugging
  • references/troubleshooting.md: Troubleshooting for LLM and hooks (Claude-specific)

For command-specific options, run wt <command> --help. For configuration, follow the workflows below.

Two Types of Configuration

Worktrunk uses two separate config files with different scopes and behaviors:

User Config (~/.config/worktrunk/config.toml)

  • Scope: Personal preferences for the individual developer
  • Location: ~/.config/worktrunk/config.toml (never checked into git)
  • Contains: LLM integration, worktree path templates, command settings, user hooks, approved commands
  • Permission model: Always propose changes and get consent before editing
  • See: references/config.md for detailed guidance

Project Config (.config/wt.toml)

  • Scope: Team-wide automation shared by all developers
  • Location: <repo>/.config/wt.toml (checked into git)
  • Contains: Hooks for worktree lifecycle (pre-start, post-start, pre-merge, etc.)
  • Permission model: Proactive (create directly, changes are reversible via git)
  • See: references/hook.md for detailed guidance

Determining Which Config to Use

When a user asks for configuration help, determine which type based on:

User config indicators:

  • "set up LLM" or "configure commit generation"
  • "change where worktrees are created"
  • "customize commit message templates"
  • Affects only their environment

Project config indicators:

  • "set up hooks for this project"
  • "automate npm install"
  • "run tests before merge"
  • Affects the entire team

Both configs may be needed: For example, setting up commit message generation requires user config, but automating quality checks requires project config.

Core Workflows

Setting Up Commit Message Generation (User Config)

Most common request. See references/llm-commits.md for supported tools and exact command syntax.

  1. Detect available tools

    which claude codex llm aichat 2>/dev/null
    
  2. If none installed, recommend Claude Code (already available in Claude Code sessions)

  3. Propose config change — Get the exact command from references/llm-commits.md

    [commit.generation]
    command = "..."  # see references/llm-commits.md for tool-specific commands
    

    Ask: "Should I add this to your config?"

  4. After approval, apply

    • Check if config exists: wt config show
    • If not, guide through wt config create
    • Read, modify, write preserving structure
  5. Suggest testing

    wt step commit --show-prompt | head  # verify prompt builds
    wt merge  # in a repo with uncommitted changes
    

Setting Up Project Hooks (Project Config)

Common request for workflow automation. Follow discovery process:

  1. Detect project type

    ls package.json Cargo.toml pyproject.toml
    
  2. Identify available commands

    • For npm: Read package.json scripts
    • For Rust: Common cargo commands
    • For Python: Check pyproject.toml
  3. Design appropriate hooks (10 hook types across 5 lifecycle events)

    • Dependencies that must finish before work starts → pre-start (blocks)
    • Long builds, dev servers, file watchers → post-start (background)
    • Tests/linting (must pass before commit) → pre-commit
    • Quality gates (must pass before merge) → pre-merge
    • Terminal/IDE updates on every switch → post-switch
    • Deployment, notifications → post-merge
    • Save artifacts before deletion → pre-remove
    • Stop servers, remove containers → post-remove
  4. Validate commands work

    npm run lint  # verify exists
    which cargo   # verify tool exists
    
  5. Create .config/wt.toml

    # Install dependencies when creating worktrees (blocks until done)
    pre-start = "npm install"
    
    # Validate code quality before committing
    [pre-commit]
    lint = "npm run lint"
    typecheck = "npm run typecheck"
    
    # Run tests before merging
    pre-merge = "npm test"
    
  6. Add comments explaining choices

  7. Suggest testing

    wt switch --create test-hooks
    

See references/hook.md for complete details.

Adding Hooks to Existing Config

When users want to add automation to an existing project:

  1. Read existing config: cat .config/wt.toml

  2. Determine hook type - When should this run?

    • Creating worktree (blocking, must finish first) → pre-start
    • Creating worktree (background, fire-and-forget) → post-start
    • Every switch (blocking) → pre-switch; (background) → post-switch
    • Before committing → pre-commit
    • Before merging → pre-merge
    • After merging → post-merge
    • Before removal → pre-remove
    • After removal → post-remove
  3. Handle format conversion if needed

    Single command to named table:

    # Before
    pre-start = "npm install"
    
    # After (adding db:migrate)
    [pre-start]
    install = "npm install"
    migrate = "npm run db:migrate"
    
  4. Preserve existing structure and comments

Validation Before Adding Commands

Before adding hooks, validate:

# Verify command exists
which npm
which cargo

# For npm, verify script exists
npm run lint --dry-run

# For shell commands, check syntax
bash -n -c "if [ true ]; then echo ok; fi"

Dangerous patterns — Warn users before creating hooks with:

  • Destructive commands: rm -rf, DROP TABLE
  • External dependencies: curl http://...
  • Privilege escalation: sudo

Permission Models

User Config: Conservative

  • Never edit without consent - Always show proposed change and wait for approval
  • Never install tools - Provide commands for users to run themselves
  • Preserve structure - Keep existing comments and organization
  • Validate first - Ensure TOML is valid before writing

Project Config: Proactive

  • Create directly - Changes are versioned, easily reversible
  • Validate commands - Check commands exist before adding
  • Explain choices - Add comments documenting why hooks exist
  • Warn on danger - Flag destructive operations before adding

Common Tasks Reference

User Config Tasks

  • Set up commit message generation → references/llm-commits.md
  • Customize worktree paths → references/config.md#worktree-path-template
  • Custom commit templates → references/llm-commits.md#templates
  • Configure command defaults → references/config.md#command-settings
  • Set up personal hooks → references/config.md#user-hooks

Project Config Tasks

  • Set up hooks for new project → references/hook.md
  • Add hook to existing config → references/hook.md#configuration
  • Use template variables → references/hook.md#template-variables
  • Add dev server URL to list → references/config.md#dev-server-url

Key Commands

# View all configuration
wt config show

# Create initial user config
wt config create

# LLM setup guide
wt config --help

Loading Additional Documentation

Load reference files for detailed configuration, hook specifications, and troubleshooting.

Find specific sections with grep:

grep -A 20 "## Setup" references/llm-commits.md
grep -A 30 "## pre-start" references/hook.md
grep -A 20 "## Warning Messages" references/shell-integration.md

Advanced: Agent Handoffs

When the user requests spawning a worktree with Claude in a background session ("spawn a worktree for...", "hand off to another agent"), use the appropriate pattern for their terminal multiplexer:

tmux (check $TMUX env var):

tmux new-session -d -s <branch-name> "wt switch --create <branch-name> -x claude -- '<task description>'"

Zellij (check $ZELLIJ env var):

zellij run -- wt switch --create <branch-name> -x claude -- '<task description>'

Requirements (all must be true):

  • User explicitly requests spawning/handoff
  • User is in a supported multiplexer (tmux or Zellij)
  • User's CLAUDE.md or explicit instruction authorizes this pattern

Do not use this pattern for normal worktree operations.

Example (tmux):

tmux new-session -d -s fix-auth-bug "wt switch --create fix-auth-bug -x claude -- \
  'The login session expires after 5 minutes. Find the session timeout config and extend it to 24 hours.'"

Example (Zellij):

zellij run -- wt switch --create fix-auth-bug -x claude -- \
  'The login session expires after 5 minutes. Find the session timeout config and extend it to 24 hours.'

What ships with it: 15 files

169.3 KB alongside SKILL.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.