claude-code-toolkit
🥈SilverCross-platform toolkit for Claude Code. Enables operations teams to automate code tasks across Linux, macOS, and Windows. Integrates with shell scripts and connects to Claude agents for code execution and management.
134140Updated 2mo ago
Intermediate30min to implementautomation
Saves ~120 min per use
Quick InstallView Source
git clone https://github.com/xixu-me/claude-code-toolkit.gitWorks with:
Claude
Overview
About This Skill
Claude Code Toolkit simplifies Claude Code installation and configuration across Linux, macOS, and Windows environments. It provides automated setup for multiple Anthropic-compatible API providers, including the official Anthropic API and services like Moonshot AI with the latest Kimi model. The toolkit handles Node.js and npm installation, manages persistent provider configurations with secure API key storage, and enables seamless switching between configured providers. Operations teams use it to standardize Claude Code deployments and reduce manual configuration overhead.
How to Use
1. **Define the task**: Specify the automation goal (e.g., 'update dependencies', 'clean build artifacts') and target platforms. Use [PLACEHOLDERS] to customize the prompt_template for your needs. 2. **Prepare the environment**: Ensure claude-code-toolkit is installed on all target systems. Verify shell access and permissions (e.g., `chmod +x` for scripts). 3. **Execute the command**: Paste the customized prompt into Claude/ChatGPT. For complex tasks, break the workflow into [STEPS] and validate outputs at each stage. Use `log_file_path` to track changes. 4. **Validate results**: Review the execution report for errors or warnings. For multi-platform tasks, compare outputs across systems to ensure consistency. 5. **Iterate if needed**: If the task fails on one platform, adjust the shell command or platform-specific logic and retry. Use the toolkit's cross-platform support to debug issues remotely.
Use Cases
Automated Claude Code installation across multiple team machines
Switching between Anthropic API and Moonshot AI Kimi model providers
Setting up custom Anthropic-compatible API providers with one command
Managing API key configurations across Linux, macOS, and Windows environments
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/xixu-me/claude-code-toolkitRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Use the claude-code-toolkit to automate [TASK_DESCRIPTION] across [PLATFORM: Linux/macOS/Windows]. Execute the following shell command: [SHELL_COMMAND]. If the task requires multi-step logic, break it into [STEPS] and validate each step's output. Log all operations to [LOG_FILE_PATH] and provide a summary of changes made.
Example Output
```
=== claude-code-toolkit Execution Report ===
Task: Automate dependency updates for a Python project across Linux, macOS, and Windows.
Platforms: Linux (Ubuntu 22.04), macOS (Ventura 13.4), Windows (10 Pro)
Step 1: Update pip and virtualenv
- Linux: ✅ Updated pip from 22.0.4 to 23.3.1
- macOS: ✅ Updated pip from 22.3.1 to 23.3.1
- Windows: ✅ Updated pip from 22.1.2 to 23.3.1
Step 2: Check outdated packages
- Linux: Found 12 outdated packages (e.g., requests 2.28.1 → 2.31.0)
- macOS: Found 10 outdated packages (e.g., numpy 1.23.5 → 1.26.2)
- Windows: Found 14 outdated packages (e.g., pandas 1.5.3 → 2.1.1)
Step 3: Generate update script
Created update_script.sh with platform-specific commands:
```bash
# Linux/macOS
pip install --upgrade $(pip list --outdated | awk 'NR>2 {print $1}')
# Windows
pip install --upgrade (pip list --outdated | Select-Object -Skip 2 | ForEach-Object { $_.Split()[0] })
```
Step 4: Execute update
- Linux: Updated 12 packages successfully
- macOS: Updated 10 packages successfully
- Windows: Updated 14 packages successfully
=== Summary ===
Total packages updated: 36
Platforms processed: 3
Time elapsed: 4m 22s
Log saved to: /reports/dependency_updates_20231115.log
```Apply to these tools
Browse all toolsClaude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Drata
Automate security compliance and monitor real-time security posture seamlessly.
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan