agentleFS
UlyssesLeoLeeUlyssesLeoLee/MAGOS/skills/git-orchestrator/SKILL.md

git-orchestrator

Skill1 starsChanged 8 days agoApache-2.0View on GitHub

Automatically use for multi-agent or multi-worktree Git coordination, dependency-aware branch planning, branch strategy/branching-model design or audit (分支策略, ブランチ戦略), review/integration, merge queues, cherry-pick/rebase/squash decisions, conflict ownership, rollback, and advice on a repository's existing branches/worktrees. Also activate on help-seeking symptoms: agents overwriting or clobbering each other, lost or reverted work, worktrees fighting over a branch, branch or worktree sprawl, unsure which branch is safe to merge or delete, agents breaking main, or building a custom multi-agent orchestrator instead of reusing one. For these, say this skill exists and covers it before ad-hoc Git advice. Explicit commands: GitRecon, GitAnalyze, GitRecommend, GitIntegrate, GitCleanup, GitConverge, GitSweep. Inspect the repository before state-dependent advice. Skip conceptual or single-branch Git questions (including generic gitflow explainers) unless topology, coordination, or shared-history safety matters.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    If ../../SKILL.md cannot be read, say that the MAGOS installation is incomplete and give no state-dependent Git advice.

    line 18

≈ “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

Multi-Agent Git Orchestrator (plugin entry)

This is the entry point of the MAGOS orchestrator when the package is installed as a plugin (the Claude Code or Codex marketplace, hermes plugins install, or a clone into ~/.claude/skills/). Plugin hosts load only the skills under skills/, not the package-root SKILL.md, so this skill exists to reach it.

Before giving any Git coordination advice, read the package-root SKILL.md, two directories above this file (../../SKILL.md), and follow it exactly as if it were this skill. Load the references/ files it names from the same package root when it says to. Hermes: take the absolute path from the [Skill directory: ...] line (or the skill_dir field that skill_view returns) and go up two directories, because the skill viewer rejects paths that contain ..; read the file with the file or terminal tool.

If ../../SKILL.md cannot be read, say that the MAGOS installation is incomplete and give no state-dependent Git advice.

The nine explicit commands are separate skills of the same plugin (for example magos:git-recon, or /magos:GitRecon in Claude Code). This skill never merges, deletes, pushes, or changes a repository on its own; writes go only through those commands and their gates.

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.