Version Control logo

Version Control

Community
wasintoh
version-control

Natural-language undo, rollback, and checkpoints that hide git entirely — "ย้อนกลับ", "undo", "ไม่เอาแล้ว", "เอาอันเดิมคืน" map to safe git stash/revert/checkpoint operations with cleanup and dev-server restart, reported in plain language. Use when the user wants to undo changes, restore a previous state, or save a safe checkpoint.

Overview

Publisherwasintoh
Repositorytoh-framework
Skill nameversion-control
Stars
96
Forks
19
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 wasintoh on GitHub. Read the source before you install it.

Installation

Install the Version Control 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/wasintoh/toh-framework.git /tmp/toh-framework
mkdir -p .claude/skills
cp -r /tmp/toh-framework/src/skills/version-control .claude/skills/version-control
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Version Control 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 Version Control 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 Version Control 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.

⏪ Version Control Skill

Purpose: Easy undo/rollback without knowing git Version: 1.0.0 Author: Toh Framework Team

Overview

This skill enables users to undo changes easily using natural language, without needing to understand git commands or version control concepts.

Core Principle

User says: "ย้อนกลับ" or "undo"
AI does: git stash/revert + cleanup + restart dev
User sees: "เรียบร้อยครับ กลับไปก่อนแก้ไขล่าสุดแล้ว"

HIDE GIT COMPLEXITY - User just says what they want.


Trigger Words

Undo/Rollback

User SaysAI Understands
ย้อนกลับUndo last change
undoUndo last change
เอาอันเดิมคืนRevert to previous
ไม่เอาแล้วDiscard current changes
กลับไปก่อนหน้าGo back to previous state
ยกเลิกที่ทำไปCancel what was done
rollbackRevert changes

Checkpoint/Save

User SaysAI Understands
save ไว้ก่อนCreate checkpoint
checkpointCreate savepoint
เซฟไว้Save current state
บันทึกจุดนี้Mark this point

Auto-Checkpoint System

AI automatically creates checkpoints at key moments:

Auto-Checkpoint Triggers

EventCheckpoint Name
After /toh-vibevibe-[project-name]-initial
After /toh-ui completionui-[component-name]-done
After /toh-dev completiondev-[feature-name]-done
After /toh-connectconnect-supabase-done
Before major changespre-[action]-backup

Checkpoint Storage

.toh/checkpoints/
├── checkpoint-log.json     # List of all checkpoints
└── (git handles actual data)

checkpoint-log.json:

json
{
  "checkpoints": [
    {
      "id": "cp-001",
      "name": "vibe-coffee-shop-initial",
      "timestamp": "2024-12-03T10:30:00Z",
      "description": "หลังสร้างโปรเจคร้านกาแฟ",
      "gitRef": "abc123"
    },
    {
      "id": "cp-002", 
      "name": "ui-dashboard-done",
      "timestamp": "2024-12-03T11:00:00Z",
      "description": "หลังสร้าง Dashboard UI",
      "gitRef": "def456"
    }
  ]
}

Undo Operations

Quick Undo (Last Change)

User: "ย้อนกลับ"

AI Process:
1. git stash or git checkout -- .
2. Restart dev server if needed
3. Confirm to user

AI Response:
"⏪ ย้อนกลับแล้วครับ!
กลับไปก่อนที่จะ [last action] แล้ว

💡 ถ้าต้องการ:
- ดูประวัติการแก้ไข พิมพ์ 'ดูประวัติ'
- ย้อนกลับไปจุดที่ save ไว้ พิมพ์ 'กลับไป [ชื่อ checkpoint]'"

Rollback to Checkpoint

User: "กลับไปก่อนแก้ไข dashboard"

AI Process:
1. Find checkpoint matching "dashboard"
2. git checkout [checkpoint-ref]
3. Restart dev server
4. Confirm to user

AI Response:
"⏪ กลับไป checkpoint 'ui-dashboard-done' แล้วครับ!
(บันทึกเมื่อ 2 ชั่วโมงก่อน)

สถานะปัจจุบัน:
- ✅ Dashboard UI เสร็จแล้ว
- ❌ การแก้ไขหลังจากนั้นถูกยกเลิก

ทำต่อได้เลยครับ!"

View History

User: "ดูประวัติ"

AI Response:
"📜 ประวัติการทำงาน:

1. 🕐 10:30 - สร้างโปรเจคร้านกาแฟ ✅
2. 🕐 11:00 - สร้าง Dashboard UI ✅
3. 🕐 11:30 - เพิ่ม POS logic ✅
4. 🕐 12:00 - ปรับ design → (ปัจจุบัน)

พิมพ์ 'กลับไป [เลข]' เพื่อย้อนกลับ
เช่น 'กลับไป 2' จะกลับไปหลังสร้าง Dashboard"

Safety Features

Before Destructive Operations

User: "ลบหน้า dashboard ทิ้ง"

AI: "⚠️ จะลบหน้า Dashboard นะครับ

ไฟล์ที่จะลบ:
- app/dashboard/page.tsx
- components/dashboard/

ยืนยันไหมครับ? (yes/no)
หรือพิมพ์ 'save ก่อน' เพื่อ backup ก่อนลบ"

Auto-Backup Before Risky Changes

AI automatically creates backup before:

  • Deleting files
  • Major refactoring
  • Changing database schema
  • /toh-connect (in case of data loss)

Git Operations Mapping

User Language → Git Commands

User SaysGit Operation
ย้อนกลับgit checkout -- . or git stash
กลับไป checkpointgit checkout [ref]
save ไว้git add . && git commit -m "[auto]"
ดูประวัติgit log --oneline
ดู diffgit diff
ลบทิ้งหมดgit reset --hard HEAD

AI Never Shows

  • Raw git commands
  • Commit hashes (use checkpoint names instead)
  • Merge conflicts (resolve automatically)
  • Git error messages (translate or fix)

Response Templates

Successful Undo

markdown
**ย้อนกลับแล้วครับ!**

กลับไปสถานะ: [checkpoint name]
เมื่อ: [time ago]

📁 ไฟล์ที่กลับคืน:
- [file list]

ทำต่อได้เลยครับ!

Checkpoint Created

markdown
💾 **บันทึก checkpoint แล้วครับ!**

ชื่อ: [checkpoint name]
เวลา: [now]

ถ้าต้องการกลับมาจุดนี้ พิมพ์:
"กลับไป [checkpoint name]"

Cannot Undo

markdown
⚠️ **ย้อนกลับไม่ได้ครับ**

เหตุผล: [reason in friendly language]

💡 แนะนำ:
- [alternative action]

Integration with Memory

Update .toh/memory/active.md after undo:

markdown
## Last Action
Undo to checkpoint: ui-dashboard-done

## Current State  
- Dashboard UI complete
- POS logic removed (was undone)

## Available Checkpoints
- vibe-coffee-shop-initial (10:30)
- ui-dashboard-done (11:00) ← current

Best Practices

DO:

  • ✅ Auto-checkpoint at key moments
  • ✅ Use friendly checkpoint names
  • ✅ Confirm before destructive operations
  • ✅ Show what will be undone

DON'T:

  • ❌ Show raw git commands
  • ❌ Show commit hashes to user
  • ❌ Allow undo without confirmation for major changes
  • ❌ Lose user's work without backup

Last Updated: 2024-12-03

Frequently asked questions

What does the Version Control AI skill do?

Natural-language undo, rollback, and checkpoints that hide git entirely — "ย้อนกลับ", "undo", "ไม่เอาแล้ว", "เอาอันเดิมคืน" map to safe git stash/revert/checkpoint operations with cleanup and dev-server restart, reported in plain language. Use when the user wants to undo changes, restore a previous state, or save a safe checkpoint.

Why use Version Control on TypingMind?

Because you install it once and use it with any model. Version Control 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 Version Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wasintoh/toh-framework/tree/main/src/skills/version-control. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Version Control?

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 Version Control?

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

Is the Version Control AI skill free?

Yes. It is published on GitHub by wasintoh 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 👇