Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
151 changes: 46 additions & 105 deletions skills/vibegit/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,50 +1,33 @@
---
name: vibegit
description: "AI-assisted version control using the Memov CLI (`mem`). Create snapshots of AI coding sessions, track file changes with prompts and responses, view interaction history, and time-travel to previous states. Use when the user mentions Memov, wants to record AI code changes, needs to review AI-assisted modifications, or asks to track prompts and responses for coding sessions."
---

# VibeGit - AI Coding History

AI-assisted version control using Memov. Track every AI interaction with your codebase.
Record AI coding sessions as snapshots using the Memov CLI. Each snapshot captures the prompt, response, changed files, and diffs.

## Prerequisites

This skill requires the `memov` Python package which provides the `mem` CLI command.

### Installation Options

Choose one of the following methods:
The `memov` Python package provides the `mem` CLI command.

```bash
# Option 1: Official install script (recommended)
# Install
curl -fsSL https://raw.githubusercontent.com/memovai/memov/main/install.sh | bash
```

### Verify Installation

```bash
# Verify
mem
```

### Initialize in Your Project

```bash
cd your-project
# Initialize in a project
mem init
```

## How to Use
## Usage Modes

There are two ways to use VibeGit:
1. **Skill scripts**: run `./scripts/*.sh` β€” thin wrappers over `mem` CLI.
2. **MCP tools (Claude Code)**: use tools like `mcp__mem-mcp__snap` β€” may add extra behavior (auto-track untracked files, auto-sync for RAG).

1. **Skill scripts (this folder)**: run `./scripts/*.sh` to call the local `mem` CLI.
2. **MCP tools (Claude Code)**: use the MCP server tools like `mcp__mem-mcp__snap`.

They are related but not identical:

- Skill scripts are a thin wrapper over `mem` CLI.
- MCP tools may add extra behavior (e.g. auto-track untracked files, auto-sync for RAG features).

## Commands

All commands should be run from the skill directory using the scripts provided.

### Core Operations
## Core Operations

| Script | Description | Usage |
|--------|-------------|-------|
Expand All @@ -55,54 +38,39 @@ All commands should be run from the skill directory using the scripts provided.
| `show.sh` | Show commit details | `./scripts/show.sh <commit_hash>` |
| `status.sh` | Check working directory status | `./scripts/status.sh` |

### Navigation
### Snap Parameters

- `--files`: Comma-separated list of modified files
- `--prompt` or `-p`: The user's original request
- `--response` or `-r`: Summary of what was done
- `--by-user` or `-u`: Mark as human edit (vs AI)

### Verify a Snapshot

After recording, confirm it was captured:

```bash
./scripts/history.sh --limit 1
```

## Navigation

| Script | Description | Usage |
|--------|-------------|-------|
| `jump.sh` | Jump to a specific snapshot | `./scripts/jump.sh <commit_hash>` |
| `branch.sh` | List/create/delete branches | `./scripts/branch.sh [name] [--delete name]` |
| `switch.sh` | Switch branches | `./scripts/switch.sh <branch_name>` |

### Web UI

Before running `mem ui start`, confirm where you want to open the UI:
## Web UI

- Which project directory should the UI read from?
- If not sure, run `pwd` and use `--loc <that path>`.

Suggested confirmation prompt:
Before starting, confirm the target project directory. If unsure, run `pwd` and pass `--loc <path>`.

| Script | Description | Usage |
|--------|-------------|-------|
| `ui_start.sh` | Start visual history browser | `./scripts/ui_start.sh [--loc /path] [--port 38888] [--foreground]` |
| `ui_stop.sh` | Stop the web server | `./scripts/ui_stop.sh [--loc /path]` |
| `ui_status.sh` | Check server status | `./scripts/ui_status.sh [--loc /path]` |

## Automatic Recording

After every AI coding session, record the interaction:

```bash
./scripts/snap.sh \
--files "api.py,tests/test_api.py" \
--prompt "Add authentication endpoint" \
--response "Added /login POST endpoint with JWT token generation"
```

### Parameters

- `--files`: Comma-separated list of files that were modified
- `--prompt` or `-p`: The user's original request
- `--response` or `-r`: Summary of what was done
- `--by-user` or `-u`: Mark as human edit (vs AI)

## RAG Features (Optional)

Some features (semantic search, validate, vibe_debug/vibe_search tools) require installing extra dependencies.

- CLI: install with `pip install memov[rag]` then run `mem sync` once.
- MCP: those tools may not appear unless RAG dependencies are installed.

## Examples

### Record a bug fix
Expand All @@ -114,6 +82,15 @@ Some features (semantic search, validate, vibe_debug/vibe_search tools) require
--response "Added null check for user object at L45"
```

### Record a feature addition

```bash
./scripts/snap.sh \
--files "api.py,tests/test_api.py" \
--prompt "Add authentication endpoint" \
--response "Added /login POST endpoint with JWT token generation"
```

### View recent history

```bash
Expand All @@ -126,58 +103,22 @@ Some features (semantic search, validate, vibe_debug/vibe_search tools) require
./scripts/jump.sh a1b2c3d
```

## Direct CLI Usage
## RAG Features (Optional)

You can also use the `mem` CLI directly:
Semantic search, validate, and vibe_debug/vibe_search tools require extra dependencies:

```bash
# Initialize
mem init

# Track new files
mem track file1.py file2.py -p "Initial tracking"

# Snapshot changes
mem snap --files file1.py -p "Added feature X" -r "Implemented..."

# View history
mem history

# Show specific commit
mem show a1b2c3d

# Jump to snapshot
mem jump a1b2c3d
pip install memov[rag]
mem sync
```

## What Gets Recorded

Each snapshot captures:
- **Prompt**: What you asked the AI to do
- **Response**: What the AI said it did
- **Files**: Which files were changed
- **Diff**: Actual code changes
- **Timestamp**: When it happened
- **Source**: AI or human

## Benefits

- **Never lose context**: Every AI interaction is recorded
- **Time travel**: Jump to any point in your coding history
- **Understand changes**: See not just what changed, but why

## Troubleshooting

### "memov CLI not found" error

If you see this error when running any script, memov is not installed. Run:

```bash
# Quick check
./install.sh

# Or install manually
pip install memov
# Or: pip install memov
```

### Scripts not executable
Expand Down