agentleFS
jaydubya818jaydubya818/multi-agent-observability/.claude/skills/create-worktree-skill/SKILL.md

create-worktree-skill

Skill2 starsChanged 9 months agoMITView on GitHub

Use when the user explicitly asks for a SKILL to create a worktree. If the user does not mention "skill" or explicitly request skill invocation, do NOT trigger this. Only use when user says things like "use a skill to create a worktree" or "invoke the worktree skill". Creates isolated git worktrees with parallel-running configuration.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 13
  2. Distinctive:

    If the branch name is not provided, stop and ask the user to provide a branch name

    line 26
  3. Distinctive:

    Use the SlashCommand tool to run:

    line 31
  4. Very specific:

    Create the git worktree in trees/<branch-name>

    line 44
  5. Distinctive:

    Start both services automatically

    line 48
  6. Very specific:

    Your response: Use SlashCommand to run /create_worktree_prompt feature-dashboard

    line 63
  7. Very specific:

    Use SlashCommand to run /create_worktree_prompt feature-a

    line 76
  8. Distinctive:

    If the command fails, common issues:

    line 89

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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 Creator Skill

This skill enables creating fully configured git worktrees for parallel development with isolated ports, databases, and configuration.

When to use this skill

Use this skill when:

  • User asks to create a git worktree
  • User wants to set up parallel development environments
  • User needs to run multiple instances simultaneously
  • User mentions working on multiple branches at once
  • User wants isolated testing environments

Instructions

Step 1: Understand the request

Extract from the user's request:

  • Branch name (required): The git branch to create the worktree from
    • If the branch name is not provided, stop and ask the user to provide a branch name
  • Port offset (optional): Custom port offset (if not provided, auto-calculated)

Step 2: Invoke the slash command

Use the SlashCommand tool to run:

/create_worktree_prompt <branch-name> [port-offset]

Examples:

  • /create_worktree_prompt feature-auth - Creates worktree with auto-calculated ports
  • /create_worktree_prompt fix-bug 2 - Creates worktree with port offset 2 (ports 4020, 5193)

Step 3: Share results

The /create_worktree_prompt command will:

  • Create the git worktree in trees/<branch-name>
  • Configure isolated ports (auto-incremented to avoid conflicts)
  • Set up environment files with proper configuration
  • Install dependencies for server and client
  • Start both services automatically
  • Provide access URLs and management instructions

Share the command output with the user, highlighting:

  • Access URLs for the dashboard
  • Ports being used
  • How to stop/restart the worktree
  • How to remove it later

Examples

Example 1: Simple worktree creation

User: "Create a worktree for the feature-dashboard branch"

Your response: Use SlashCommand to run /create_worktree_prompt feature-dashboard

Example 2: Worktree with specific port offset

User: "Set up a parallel environment on branch hotfix-security with port offset 5"

Your response: Use SlashCommand to run /create_worktree_prompt hotfix-security 5

Example 3: Multiple worktrees

User: "I need worktrees for branches: feature-a, feature-b, and feature-c"

Your response:

  1. Use SlashCommand to run /create_worktree_prompt feature-a
  2. Use SlashCommand to run /create_worktree_prompt feature-b
  3. Use SlashCommand to run /create_worktree_prompt feature-c

Each will automatically get unique ports (4010/5183, 4020/5193, 4030/5203).

Related capabilities

  • The created worktree will run automatically with isolated ports, database, and configuration
  • Each worktree is completely independent and can run simultaneously with others

Troubleshooting

If the command fails, common issues:

  • Branch name already exists as a worktree
  • Ports are in use (command kills them automatically)
  • Missing dependencies (ensure bun is installed)
  • Git worktree errors (handle uncommitted changes first)

The slash command provides detailed error messages and suggestions.

Download now (ZIP)

  • Other versions2 projects use a version of this.

    Word for word · 2

    1. disler/claude-code-hooks-multi-agent-observability★ 1.5k100% same
    2. CodeWithBehnam/cc-docs★ 2100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

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.