spawn-terminal
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.
Best use case
spawn-terminal is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.
Teams using spawn-terminal should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/terminal/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How spawn-terminal Compares
| Feature / Agent | spawn-terminal | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Purpose
Spawn a new terminal window to execute CLI commands. This skill is for generic command execution, NOT for spawning AI agents. For AI agents, use the `spawn:agent` skill instead.
## Variables
| Variable | Default | Description |
|----------|---------|-------------|
| LOG_TO_FILE | false | Write full terminal output to debug file |
| CAPTURE | false | Block and return output directly |
## Instructions
**MANDATORY** - You MUST follow the Workflow steps below in order. Do not skip steps.
1. Identify the CLI command the user wants to run
2. Run `<command> --help` first to verify syntax and options
3. Execute the command in a new terminal using `fork_terminal()`
## Red Flags - STOP and follow Cookbook
If you're about to:
- Execute a command without checking its --help first
- Assume you know the command syntax
- Skip the --help step "because it's simple"
- Spawn an AI agent (use `spawn:agent` instead)
**STOP** -> Run `<command> --help` first -> Review output -> Then proceed
## Workflow
**MANDATORY CHECKPOINTS** - Verify each before proceeding:
1. [ ] Understand the user's request
2. [ ] **VERIFY**: This is a CLI command, NOT an AI agent request
3. [ ] READ: '../agent/fork_terminal.py' to understand the tooling
4. [ ] Follow the Cookbook: Read './cookbook/cli-command.md'
5. [ ] **CHECKPOINT**: Ran `<command> --help` and reviewed options
6. [ ] Execute fork_terminal(command, log_to_file=False, log_agent_output=False)
## Cookbook
### CLI Commands
- IF: User requests any non-AI CLI command (ffmpeg, curl, python, npm, etc.)
- THEN: Read and execute './cookbook/cli-command.md'
- Examples:
- "Create a new terminal to run ffmpeg"
- "Spawn terminal with curl"
- "Fork a terminal to run python script.py"
- "New terminal: npm run build"
## Usage
The `fork_terminal()` function is located at `../agent/fork_terminal.py`:
```python
from spawn.agent.fork_terminal import fork_terminal
# Simple command execution (no output capture)
fork_terminal("npm run build")
# With debug output capture
file_path = fork_terminal("ffmpeg -i video.mp4 output.gif", log_to_file=True)
# Blocking capture (waits for completion)
output = fork_terminal("python script.py", capture=True, log_to_file=True)
```
## When to Use spawn:agent Instead
If the user mentions any of these, use `spawn:agent`:
- Claude, Claude Code
- Codex, OpenAI
- Gemini, Google
- Cursor
- OpenCode
- Copilot, GitHub Copilot
- "AI agent", "coding agent", "spawn agent"Related Skills
terminal-session
tmux 持久化终端会话控制。通过向 tmux 发送按键、读取输出,管理 Claude Code、Codex、SSH 等长时间运行的交互式进程。跨多轮对话保持进程状态。需预装 tmux(Linux/macOS 默认提供;Windows 用户需 WSL2)。
spawn-agent
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
spawn
Skills for spawning external processes - AI coding agents and generic CLI commands in new terminal windows. Parent skill category for agent and terminal spawning.
spawn-parallel
Pattern for spawning parallel subagents efficiently. Use when you need multiple independent tasks done concurrently.
terminal-title
This skill should be used to update terminal window title with context. Triggers automatically at session start via hook. Also triggers on topic changes during conversation (debugging to docs, frontend to backend). Updates title with emoji + project + current topic.
Warp — Modern Terminal & Workflow Automation
## Overview
OpenAI Codex CLI — AI Coding Agent in Your Terminal
You are an expert in OpenAI's Codex CLI, the open-source terminal-based coding agent that reads your codebase, generates and edits code, runs shell commands, and applies changes — all within your terminal. You help developers use Codex CLI for code generation, refactoring, debugging, and automation with configurable approval modes (suggest, auto-edit, full-auto) and sandboxed execution for safety.
Gemini CLI — Google's AI Coding Agent for the Terminal
You are an expert in Gemini CLI, Google's open-source terminal-based AI agent powered by Gemini models. You help developers use Gemini CLI for code generation, file editing, shell command execution, and multi-modal tasks (analyzing images, reading PDFs) — with Google's 1M+ token context window for understanding entire codebases at once and MCP tool integration for extending capabilities.
Amazon Q (formerly Fig) — Terminal Autocomplete & CLI Tools
## Overview
Claude Code — Terminal AI Coding Agent
## Overview
Aider — AI Pair Programming in Your Terminal
You are an expert in Aider, the terminal-based AI coding assistant that reads your codebase, makes changes across multiple files, and creates proper git commits. You help developers use Aider for autonomous code generation, refactoring, bug fixing, and test writing — working with any LLM (Claude, GPT-4, Gemini, local models) while respecting project conventions and maintaining git history.
Daily Logs
Record the user's daily activities, progress, decisions, and learnings in a structured, chronological format.