agentleFS
yk-tanigawayk-tanigawa/repo-template/.claude/skills/git-cleanup/SKILL.md

git-cleanup

Skill0 starsChanged 17 days agoMIT-0View on GitHub

Use when local git worktrees or branches have piled up in a checkout of this repository and the person wants to tidy them, such as "clean up old branches", "remove merged worktrees", "what can I delete in .claude/worktrees", or after a batch of pull requests merges. Runs the dry-run cleanup script, shows what it would delete, and leaves the deletion and any remote-branch deletion to the person.

  • Commits and pushes

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use skill-creator.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the dry run, make git-cleanup, and show its whole output: the DELETE and KEEP lines, the unmerged commits, the remote list, and any …

    line 21
  2. Distinctive:

    After they run it, run the dry run again and report what is left.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 8 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

Clean Up Merged Branches and Worktrees

Canonical doc: docs/local-development.md ("Git Housekeeping"). Read it before running anything. This skill gives the order of the steps and holds no rules of its own.

What you decide

These stay with the person; ask, do not choose:

  • whether to run --execute after reading the dry run;
  • whether any unmerged branch can be dropped with --include-unmerged;
  • whether to delete the remote branches the script lists.

Steps

  1. Fast-forward main first, so "in origin/main" reflects what has merged.
  2. Run the dry run, make git-cleanup, and show its whole output: the DELETE and KEEP lines, the unmerged commits, the remote list, and any note that open pull requests were not checked.
  3. For each unmerged branch, say what its commits are and whether they reached main another way (for example, a squash merge, or a pull request merged into another branch instead of main). Do not call a branch safe to drop without that check.
  4. For a worktree kept for uncommitted changes, compare those changes with main and report the result; do not discard them.
  5. Give the person the commands to run: make git-cleanup with GIT_CLEANUP_ARGS=--execute (and --include-unmerged only if they chose it), and the printed git push origin --delete line for remote branches. They run these themselves, for example with ! in the Claude Code prompt.
  6. After they run it, run the dry run again and report what is left.

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.