Git Sync logo

Git Sync

Community
EricTechPro
git-sync

Sync the current branch in one pass — commit the working tree as one commit per logical change (in the host repo's commit format, or the super-board writing standard), gate Supabase schema changes, merge-pull, resolve conflicts hunk by hunk, then push without force. Use when the user runs /git-sync or says "git-sync", "sync", "commit and push", "pull and push", or "sync my branch".

Overview

PublisherEricTechPro
Repositorysuper-board
Skill namegit-sync
Stars
464
Forks
136
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Git 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.
    https://github.com/EricTechPro/super-board/tree/main/skills/git-sync
  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/EricTechPro/super-board.git /tmp/super-board
mkdir -p .claude/skills
cp -r /tmp/super-board/skills/git-sync .claude/skills/git-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Git 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 Git 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 Git 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.

/git-sync

Commit what is in the working tree, pull, push, report. One step per line. Stop and tell the user when a step says stop. NEVER force push, rebase shared history, or skip a hook (--no-verify).

1 · Look

  1. Run git status, git branch --show-current and git rev-parse --abbrev-ref @{upstream}.
  2. Run git fetch and git rev-list --left-right --count HEAD...@{upstream} for ahead/behind.
  3. Stop on a detached HEAD.
  4. Stop when a merge, rebase, cherry-pick or revert is in progress that this run did not start (.git/MERGE_HEAD, .git/rebase-merge, .git/rebase-apply, .git/CHERRY_PICK_HEAD).
  5. Nothing to commit and nothing ahead or behind: say "in sync" and stop.

2 · Commit

  1. Read the diff (git diff, git diff --staged, untracked files) and group it into logical changes. One change, one commit.
  2. Stage each group by explicit path (git add -- <path>…). NEVER git add -A, git add . or git commit -a.
  3. NEVER stage secrets: .env* (except .env.example), keys (*.pem, *.key, id_rsa*), credential or token files, or a diff line that holds a key. Stop and warn, naming the file.
  4. A file that looks like someone else's work in progress (another task's half-edit, a file you can't explain from this conversation): leave it unstaged and list it in the report.
  5. Changes already staged by the user are one group; commit them as they are.
  6. Run the Supabase gate (section 3) before any commit that touches supabase/.
  7. Commit each group. Let the hooks run; a failing hook is a stop, not a retry with --no-verify.

Commit format. The host wins.

  1. The host's AGENTS.md, CLAUDE.md or CONTRIBUTING.md defines a commit format: follow it (for example #N: type: description).
  2. Otherwise use section "1 · Commit" of the super-board writing standard (.claude/skills/super-board/references/writing-standard.md): emoji, [type], scope, subject, 1–4 bullets, Closes #N when the commit finishes a ticket.
  3. Keep any attribution trailer the session asks for.

3 · Supabase gate

Runs only when a commit group touches supabase/ (migrations, schema, functions).

  1. The supabase skill is installed: follow its "Making and Committing Schema Changes" section and skip the rest of this list.
  2. Each schema change has its own migration file named the way supabase migration new <name> names it (supabase/migrations/<timestamp>_<name>.sql). A schema edit with no migration is a stop.
  3. When the CLI and local stack are up, run supabase migration list --local.
  4. Run supabase db advisors (or the Supabase MCP get_advisors) when available.
  5. An advisor error is a stop. Warnings go in the report.
  6. CLI or stack not available: say which checks were skipped and why, then continue.

4 · Pull

  1. Run git pull --no-rebase. Merge, never rebase.
  2. No conflict: go to Push.
  3. Conflict: use the resolving-merge-conflicts skill when it is installed.
  4. Without it, resolve hunk by hunk and keep both sides' intent.
  5. NEVER use -X ours, -X theirs, git checkout --ours/--theirs on a whole file, or delete a side to make the conflict go away.
  6. A hunk whose intent is unclear: stop and ask the user, showing both sides.
  7. Run the host's fast checks before concluding the merge: typecheck, lint and tests as the host's AGENTS.md, CLAUDE.md or package.json documents them.
  8. Checks fail: fix the merge, not the checks. Still failing: stop and report.
  9. Conclude with git commit --no-edit.

5 · Push

  1. The branch has an upstream: git push.
  2. A new branch: git push -u origin <branch>.
  3. NEVER --force or --force-with-lease.
  4. The branch is the default or a protected branch (main, master, production, or the repo's default from gh repo view --json defaultBranchRef): push only after the user says yes in this conversation. Otherwise offer a branch and a PR instead.
  5. Push rejected as non-fast-forward: go back to Pull once. Rejected again: stop.

6 · Report

Keep it short:

Committed  <sha> <subject>
           <sha> <subject>
Pulled     <N> commits (<conflicts resolved: N files | no conflicts>)
Pushed     <N> commits to <remote>/<branch>
Left out   <path> — <why>
Supabase   <advisors clean | N warnings | skipped: why>

Drop the lines that do not apply.

Frequently asked questions

What does the Git Sync AI skill do?

Sync the current branch in one pass — commit the working tree as one commit per logical change (in the host repo's commit format, or the super-board writing standard), gate Supabase schema changes, merge-pull, resolve conflicts hunk by hunk, then push without force. Use when the user runs /git-sync or says "git-sync", "sync", "commit and push", "pull and push", or "sync my branch".

Why use Git Sync on TypingMind?

Because you install it once and use it with any model. Git 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 Git Sync in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EricTechPro/super-board/tree/main/skills/git-sync. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Git 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 Git Sync?

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

Is the Git Sync AI skill free?

Yes. It is published on GitHub by EricTechPro 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 👇