Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Auto Claude Setup

FSecurity

Complete Auto-Claude installation and setup guide for all platforms. Use when installing Auto-Claude on WSL, Windows, Linux, or macOS, setting up development environment, or troubleshooting installation issues.

207 stars
0 votes
0 copies
0 views
Added 9/4/2026
ai-agentspythonc++shellbashnodenodejsdebugginggitapifrontend

Works with

claude codeterminalcliapi

Security Analysis

F38/100
criticalPipes output to a shell interpreter
mediumUses curl or wget to download content
criticalModifies startup scripts or system services for persistence
criticalExfiltrates credentials via HTTP — exact pattern from Snyk ToxicSkills study
criticalDownloads and executes remote scripts — classic supply chain attack
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/4/2026

Install to Claude Code

$npx -y skills add NeverSight/skills_feed --skill auto-claude-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Auto Claude Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Auto Claude Setup
[![Security: F — Skills Directory](https://www.skillsdirectory.com/api/skills/neversight-auto-claude-setup/badge)](https://www.skillsdirectory.com/skills/neversight-auto-claude-setup)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: auto-claude-setup
description: Complete Auto-Claude installation and setup guide for all platforms. Use when installing Auto-Claude on WSL, Windows, Linux, or macOS, setting up development environment, or troubleshooting installation issues.
version: 1.0.0
auto-claude-version: 2.7.2
---

# Auto-Claude Setup

Complete installation and environment setup for the Auto-Claude autonomous coding framework.

## Quick Start

### Prerequisites

| Requirement | Version | Notes |
|-------------|---------|-------|
| Python | 3.12+ | Required for backend and Memory Layer |
| Node.js | 24+ | Required for frontend |
| npm | 10+ | Package manager |
| Git | Latest | Version control |
| Claude Pro/Max | Active | Subscription required |
| Claude Code CLI | Latest | `npm install -g @anthropic-ai/claude-code` |

### Installation Methods

#### Method 1: Pre-built Release (Recommended)

Download from [GitHub Releases](https://github.com/AndyMik90/Auto-Claude/releases/latest):

| Platform | Download |
|----------|----------|
| Windows | Auto-Claude-2.7.2.exe |
| macOS (Apple Silicon) | Auto-Claude-2.7.2-arm64.dmg |
| macOS (Intel) | Auto-Claude-2.7.2-x64.dmg |
| Linux (Universal) | Auto-Claude-2.7.2.AppImage |
| Linux (Debian) | Auto-Claude-2.7.2.deb |

#### Method 2: From Source (Development)

```bash
# Clone repository
git clone https://github.com/AndyMik90/Auto-Claude.git
cd Auto-Claude

# Install all dependencies
npm run install:all

# Run in development mode
npm run dev

# Or build and run
npm start
```

## Platform-Specific Setup

### WSL2 (Windows Subsystem for Linux)

```bash
# 1. Ensure WSL2 is updated
wsl --update

# 2. Install Python 3.12
sudo apt update && sudo apt install -y python3.12 python3.12-venv python3.12-dev

# 3. Install Node.js 24+ via nvm
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.0/install.sh | bash
source ~/.bashrc
nvm install 24
nvm use 24

# 4. Clone and setup
git clone https://github.com/AndyMik90/Auto-Claude.git
cd Auto-Claude
npm run install:all

# 5. Setup OAuth token
claude setup-token
```

### Windows (Native)

```powershell
# 1. Install Python 3.12
winget install Python.Python.3.12

# 2. Install Node.js 24
winget install OpenJS.NodeJS.LTS

# 3. Install Claude Code CLI
npm install -g @anthropic-ai/claude-code

# 4. Clone and setup
git clone https://github.com/AndyMik90/Auto-Claude.git
cd Auto-Claude
npm run install:all
```

### Linux (Ubuntu/Debian)

```bash
# 1. Install Python 3.12
sudo apt update
sudo apt install -y python3.12 python3.12-venv python3.12-dev

# 2. Install Node.js 24 via NodeSource
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt install -y nodejs

# 3. Install Claude Code CLI
sudo npm install -g @anthropic-ai/claude-code

# 4. Clone and setup
git clone https://github.com/AndyMik90/Auto-Claude.git
cd Auto-Claude
npm run install:all
```

### macOS

```bash
# 1. Install Homebrew (if not installed)
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# 2. Install Python 3.12 and Node.js
brew install python@3.12 node@24

# 3. Install Claude Code CLI
npm install -g @anthropic-ai/claude-code

# 4. Clone and setup
git clone https://github.com/AndyMik90/Auto-Claude.git
cd Auto-Claude
npm run install:all
```

## Authentication Setup

### OAuth Token Configuration

```bash
# Generate OAuth token (opens browser for authentication)
claude setup-token

# Token is saved to:
# - macOS: Keychain
# - Windows: Credential Manager
# - Linux: ~/.config/claude/credentials
```

### Environment Configuration

Create `apps/backend/.env` from the example:

```bash
cd apps/backend
cp .env.example .env
```

**Required Configuration:**

```bash
# OAuth token (if not using keychain)
CLAUDE_CODE_OAUTH_TOKEN=your-oauth-token-here
```

**Optional Configuration:**

```bash
# Model override (default: claude-opus-4-5-20251101)
AUTO_BUILD_MODEL=claude-opus-4-5-20251101

# Default git branch
DEFAULT_BRANCH=main

# Debug mode
DEBUG=true
DEBUG_LEVEL=2

# Linear integration
LINEAR_API_KEY=lin_api_xxxxx

# Memory system (Graphiti)
GRAPHITI_ENABLED=true
GRAPHITI_LLM_PROVIDER=openai
OPENAI_API_KEY=sk-xxxxx
```

## Verification

### Test Installation

```bash
# Check Python version
python3 --version  # Should be 3.12+

# Check Node.js version
node --version  # Should be 24+

# Check Claude Code CLI
claude --version

# Test backend
cd apps/backend
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
python run.py --help

# Test frontend
cd apps/frontend
npm run dev
```

### Run First Task

```bash
cd apps/backend
source .venv/bin/activate

# Create a spec interactively
python spec_runner.py --interactive

# Or with a task description
python spec_runner.py --task "Add a hello world endpoint"
```

## Project Structure

```
Auto-Claude/
├── apps/
│   ├── backend/           # Python CLI and agents
│   │   ├── agents/        # Agent implementations
│   │   ├── core/          # Client, auth, security
│   │   ├── prompts/       # Agent system prompts
│   │   ├── spec/          # Spec creation pipeline
│   │   ├── .env           # Your configuration
│   │   └── run.py         # Main entry point
│   └── frontend/          # Electron desktop UI
├── guides/                # Documentation
├── tests/                 # Test suite
└── scripts/               # Build utilities
```

## Common Issues

### Windows: node-gyp Errors

Install Visual Studio Build Tools:
1. Download [Visual Studio Build Tools 2022](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
2. Select "Desktop development with C++" workload
3. Add "MSVC v143 - VS 2022 C++ x64/x86 Spectre-mitigated libs"
4. Restart terminal and run `npm install` again

### Python Version Mismatch

```bash
# Check which Python is being used
which python3
python3 --version

# Create venv with specific Python version
python3.12 -m venv .venv
```

### OAuth Token Issues

```bash
# Re-run token setup
claude setup-token

# Verify token is set
echo $CLAUDE_CODE_OAUTH_TOKEN

# Check Claude Code is working
claude --version
```

## Related Skills

- **auto-claude-cli**: Core CLI operations
- **auto-claude-spec**: Spec creation workflow
- **auto-claude-memory**: Memory system configuration
- **auto-claude-troubleshooting**: Debugging guide

## References

- [Official README](https://github.com/AndyMik90/Auto-Claude/blob/main/README.md)
- [Contributing Guide](https://github.com/AndyMik90/Auto-Claude/blob/main/CONTRIBUTING.md)
- [CLI Usage Guide](https://github.com/AndyMik90/Auto-Claude/blob/main/guides/CLI-USAGE.md)

Attribution

NeverSightNeverSight
View sourceMore from NeverSight →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →