Repo Sync logo

Repo Sync

CommunityPopular
davidondrej
repo-sync

Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.

Overview

Publisherdavidondrej
Repositoryskills
Skill namerepo-sync
Stars
4.1K
Forks
599
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by davidondrej on GitHub. Read the source before you install it.

Installation

Install the Repo Sync AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davidondrej/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/ops-and-setup/repo-sync .claude/skills/repo-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Sync in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Repo Sync on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Repo Sync is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

repo-sync

What it does

Sync shared Git repos for team documents, notes, skills, and context on macOS. Complex software projects and pull request workflows are outside scope.

By default, after 60 seconds without local edits, repo-sync commits eligible non-ignored changes (including staged edits, renames, and deletions), rebases, and pushes. It checks remote changes every 60 seconds and starts at login without an AI agent.

Only the remote's default branch syncs (origin/HEAD, falling back to main). Feature branches and detached HEAD are skipped; branches are never switched.

Check first

sh
command -v repo-sync
repo-sync help

Installed help is the command contract. Older binaries may lack skill, remove, status, or version; run repo-sync version when listed. Installing the skill does not install or upgrade the binary.

Default config: ~/Library/Application Support/repo-sync/config.json. Check ProgramArguments in ~/Library/LaunchAgents/com.vectal-labs.repo-sync.plist for a custom path and use the selected config throughout. Flags precede positional arguments.

Read references/operations.md for custom settings, unsupported commands, legacy removal, upgrades, or failed checks.

Start syncing

A request to sync a named repo authorizes automatic commits and pushes. Mention that staged changes are included; do not ask again when already authorized.

For a fresh installation:

sh
brew install --cask vectal-labs/tap/repo-sync
repo-sync setup
repo-sync status

Homebrew must already be available; it installs Git and GitHub CLI. Setup checks identity/access and service health, and preserves existing registrations. Select only requested repos.

For an existing local clone:

sh
repo-sync add "/absolute/path/to/notes"
repo-sync status

add defaults to the current repo, which needs an origin remote. When asked to clone a remote repo, check the destination, clone, then add it. Do not overwrite folders, create remote repos, or change remotes without authorization.

For a custom config:

sh
repo-sync add --config "/absolute/path/to/config.json" "/absolute/path/to/notes"
repo-sync status --config "/absolute/path/to/config.json"

add may save registration despite restart failure. Check fresh status; if setup is needed, use the same config. Report registration separately from active syncing when readiness fails.

Stop syncing one repo

When installed help lists remove:

sh
repo-sync remove "/absolute/path/to/notes"
repo-sync status
sh
repo-sync remove --config "/absolute/path/to/config.json" "/absolute/path/to/notes"
repo-sync status --config "/absolute/path/to/config.json"

remove defaults to the current repo. For missing or moved folders, use the old configured absolute path.

Removal unregisters the repo and restarts the matching service. Files, history, local work, and pushed data remain; teammates' syncing is unaffected. In-progress Git operations may finish during shutdown.

Verify registration is absent and the service applied the change. Removing the last repo leaves an empty running service. With no background service, only config changes; manually started repo-sync run processes still need restarting.

Without remove, follow Legacy removal in the reference. Do not uninstall or delete the clone instead.

Install or maintain this skill

When help lists skill, use repo-sync skill install, then repo-sync skill status. The binary bundles the skill and references; no checkout or download is needed. Setup also offers installation. Start a new agent session afterward.

Homebrew upgrades refresh unchanged managed copies. After Go upgrades, rerun setup or repo-sync skill refresh. repo-sync skill uninstall removes unchanged managed copies, preserving customized folders, the program, and syncing service. See Agent skill installation in the reference for destinations and conflicts.

Uninstall everything

Run repo-sync uninstall only on request. After confirmation, it removes the service, settings, logs, cache, program, and unchanged managed skills. Customized skills, repositories, Git history, and shared Git credentials remain. --keep-binary retains the program; --yes skips the prompt when already authorized.

Safety and verification

  • Filename protection blocks names such as .env, private keys, and .npmrc, but does not scan contents; ordinary filenames can hide secrets. Normal syncing can unstage blocked files.
  • Use repo-sync allow only when publishing that file is explicitly authorized.
  • Conflicts preserve local commits, abort repo-sync's own rebase, and retry. No automatic conflict resolution or force-push; one failing repo does not block others.
  • Do not reset history, switch branches, delete lock files, or override secret protection just to clear an error.
  • There is no pause, resume, or sync now command. Check help before using any command.
  • Check exit codes and fresh status; a running service can still have repo failures. Do not create verification commits or push test files without authorization.
  • Briefly report the repo, action, verification, and remaining failures.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Repo Sync AI skill do?

Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.

Why use Repo Sync on TypingMind?

Because you install it once and use it with any model. Repo Sync is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Repo Sync in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davidondrej/skills/tree/main/skills/ops-and-setup/repo-sync. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Repo Sync?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Repo Sync?

As many as you like. As long as a model supports skills, you can use Repo Sync with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Repo Sync AI skill free?

Yes. It is published on GitHub by davidondrej under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇