Rollback

Organization

ww-w-ai

rollback

Manage checkpoints and rollback for safe recovery. Create restore points before risky operations and restore to previous states when needed. Use proactively when user mentions rollback, undo, restore, checkpoint, or recovery. Triggers: rollback, checkpoint, restore, undo, revert, recovery, save point, 롤백, 체크포인트, 복원, 되돌리기, 복구, ロールバック, チェックポイント, 復元, 元に戻す, 回滚, 检查点, 恢复, 撤销, restaurar, punto de control, revertir, deshacer, restaurer, point de contrôle, annuler, revenir, Wiederherstellung, Prüfpunkt, rückgängig machen, ripristino, checkpoint, annullare, ripristinare Do NOT use for: git operations (use git directly), file editing

Overview

Publisher	ww-w-ai
Repository	`bkit-gemini`
Skill name	`rollback`
Stars	66
Forks	16
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

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 ww-w-ai on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/ww-w-ai/bkit-gemini.git /tmp/bkit-gemini
mkdir -p .claude/skills
cp -r /tmp/bkit-gemini/skills/rollback .claude/skills/rollback

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rollback 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 Rollback 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 Rollback 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.

Rollback Skill

Create, list, and restore checkpoints for safe recovery

Commands

Command	Description	Example
`/rollback create`	Create a new checkpoint	`/rollback create "before refactor"`
`/rollback list`	List all checkpoints	`/rollback list`
`/rollback restore [id]`	Restore to a checkpoint	`/rollback restore chk-20260409-143000`
`/rollback diff [id]`	Show changes since checkpoint	`/rollback diff chk-20260409-143000`

MCP Integration

This skill uses the bkit_checkpoint MCP tool to manage checkpoints.

How to Execute

Create Checkpoint

Call bkit_checkpoint with action create
Optionally include a label for easy identification
The tool snapshots the current state of tracked files
Returns a checkpoint ID (format: chk-YYYYMMDD-HHMMSS)
Display confirmation with the checkpoint ID

List Checkpoints

Call bkit_checkpoint with action list
Display checkpoints in reverse chronological order
Show: ID, timestamp, label, file count, size

Restore Checkpoint

Call bkit_checkpoint with action restore and the checkpoint ID
Important: Automatically create a new checkpoint before restoring (safety net)
Restore files to the checkpoint state
Display list of files changed/restored
Warn about any files that were added after the checkpoint (they will remain)

Show Diff

Call bkit_checkpoint with action diff and the checkpoint ID
Compare current state against the checkpoint
Show added, modified, and deleted files
Display line-level diff for modified files

Checkpoint Storage

Checkpoints are stored in .bkit/checkpoints/:


.bkit/checkpoints/
  chk-20260409-143000/
    manifest.json    # List of files and their hashes
    label.txt        # Optional label
    files/           # Snapshot of tracked files

Manifest Format

json
{
  "id": "chk-20260409-143000",
  "timestamp": "2026-04-09T14:30:00Z",
  "label": "before refactor",
  "files": [
    {
      "path": "src/api/auth.js",
      "hash": "sha256:abc123...",
      "size": 2456
    }
  ],
  "totalFiles": 12,
  "totalSize": 34567
}

Auto-Checkpoint Triggers

Checkpoints are automatically created by hooks in these situations:

Before deployment (/deploy)
Before PDCA iterate phase
Before bulk file operations (10+ files)

Output Format

markdown
## Checkpoint Created

- **ID**: chk-20260409-143000
- **Label**: before refactor
- **Files**: 12 tracked files
- **Size**: 34.5 KB

Use `/rollback restore chk-20260409-143000` to restore.

Safety Rules

Always create backup before restoring (double safety net)
Never delete checkpoints automatically - user must manage
Warn on old checkpoints - flag if restoring to a checkpoint older than 24 hours
Show diff first - recommend /rollback diff before /rollback restore

Frequently asked questions

What does the Rollback AI skill do?

Why use Rollback on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ww-w-ai/bkit-gemini/tree/main/skills/rollback. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rollback?

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 Rollback?

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

Is the Rollback AI skill free?

Yes. It is published on GitHub by ww-w-ai under the Apache-2.0 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

Requesting Code Review

obra

CommunityPopular

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Systematic Debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Test Driven Development

obra

CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

Using Git Worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Rollback Skill

Commands

MCP Integration

How to Execute

Create Checkpoint

List Checkpoints

Restore Checkpoint

Show Diff

Checkpoint Storage

Manifest Format

Auto-Checkpoint Triggers

Output Format

Safety Rules

Frequently asked questions

Related AI Skills

Set up your own AI workspace now