agentleFS
jjanuszczakjjanuszczak/margo/skills/git-workflow-lifecycle/SKILL.md

git-workflow-lifecycle

Skill2 starsChanged 17 days agoApache-2.0View on GitHub

Automate the end-to-end lifecycle of a feature branch, from submission (commit, push, PR) to cleanup (merge check, sync main, delete branch). Use when you have finished work on a branch or when a PR has been merged and you need to clean up.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 when you have finished implementation on a branch and are ready for review.

    line 13
  2. Distinctive:

    Use this after your Pull Request has been merged on GitHub.

    line 22
  3. Very specific:

    Ensure gh CLI is authenticated.

    line 30
  4. Very specific:

    Analyze Report: Read results in .gemini/skills/git-workflow-lifecycle/evals/reports/latest_submit_results.json.

    line 45
  5. Very specific:

    Self-Correction: If the PR is missing or not linked, attempt to fix the PR body using gh pr edit.

    line 46
  6. Distinctive:

    Self-Correction: If branches remain, manually delete them (git branch -D or git push origin --delete) and ensure you are on main.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Git Workflow Lifecycle

This skill manages the transition of code from a local development branch to GitHub and the subsequent cleanup once the work is merged.

Workflows

1. Submit Work

Use this when you have finished implementation on a branch and are ready for review.

  • Action: Stages all changes, commits with a message, pushes to origin, and creates a GitHub Pull Request.
  • Linkage: Automatically adds "Closes #XX" if an issue number is detected in the branch name.
python3 .gemini/skills/git-workflow-lifecycle/scripts/submit_work.py --message "feat: description of work"

2. Cleanup Branch

Use this after your Pull Request has been merged on GitHub.

  • Action: Verifies the PR is merged, switches to main, pulls latest updates, and deletes both local and remote branches.
python3 .gemini/skills/git-workflow-lifecycle/scripts/cleanup_branch.py

Instructions

  • Ensure gh CLI is authenticated.
  • The submit_work.py script will prompt for a commit message if --message is omitted.
  • The cleanup_branch.py script will warn you if the PR is not yet merged before proceeding with deletion.

Scripts

  • scripts/submit_work.py
  • scripts/cleanup_branch.py

Self-Evaluation & Correction

You MUST autonomously verify every git workflow task:

1. Verify Submission

Immediately after running submit_work.py:

  1. Run Evaluation Suite: python3 .gemini/skills/git-workflow-lifecycle/evals/runner.py submit <branch_name>
  2. Analyze Report: Read results in .gemini/skills/git-workflow-lifecycle/evals/reports/latest_submit_results.json.
  3. Self-Correction: If the PR is missing or not linked, attempt to fix the PR body using gh pr edit.

2. Verify Cleanup

Immediately after running cleanup_branch.py:

  1. Run Evaluation Suite: python3 .gemini/skills/git-workflow-lifecycle/evals/runner.py cleanup <branch_name>
  2. Analyze Report: Read results in .gemini/skills/git-workflow-lifecycle/evals/reports/latest_cleanup_results.json.
  3. Self-Correction: If branches remain, manually delete them (git branch -D or git push origin --delete) and ensure you are on main.

<AVAILABLE_RESOURCES>

  • Evaluation Runner: .gemini/skills/git-workflow-lifecycle/evals/runner.py </AVAILABLE_RESOURCES>

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.