agentleFS
HarambeeAIHarambeeAI/bayes-ship/skills/ship-worktree/SKILL.md

ship-worktree

Skill1 starsChanged 7 months agoMITView on GitHub

Create an isolated git worktree for feature implementation. Verifies clean test baseline before work begins. Run after architecture approval.

The file

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. Very specific:

    Create a new git branch: feature/<project-name>-v1 (or use phase number if building incrementally).

    line 10
  2. Very specific:

    Create a git worktree in an isolated directory: ../<project-name>-worktree.

    line 11
  3. Distinctive:

    Run project setup in the worktree: install dependencies, build.

    line 12
  4. Distinctive:

    Verify clean test baseline: Run the full test suite. ALL existing tests must pass.

    line 13
  5. Distinctive:

    If tests fail: STOP. Surface failures to the user.

    line 14
  6. Distinctive:

    If no tests exist (new project): note this and proceed.

    line 15
  7. Very specific:

    If use_worktrees is set to false in settings, skip worktree creation and work in the current directory.

    line 21
  8. Distinctive:

    If a worktree already exists for this project, ask the user whether to reuse or create a new one.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 — Isolated workspace setup

Process

  1. Create a new git branch: feature/<project-name>-v1 (or use phase number if building incrementally).
  2. Create a git worktree in an isolated directory: ../<project-name>-worktree.
  3. Run project setup in the worktree: install dependencies, build.
  4. Verify clean test baseline: Run the full test suite. ALL existing tests must pass.
    • If tests fail: STOP. Surface failures to the user. Do NOT start implementation on a broken baseline.
    • If no tests exist (new project): note this and proceed.
  5. Record worktree location in progress.json.
  6. Output: "Workspace ready. Run /bayes-ship:ship-plan 1 to plan Phase 1."

Rules

  • If use_worktrees is set to false in settings, skip worktree creation and work in the current directory. Still verify test baseline.
  • If a worktree already exists for this project, ask the user whether to reuse or create a new one.

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.