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.
Best use case
spawn is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Skills for spawning external processes - AI coding agents and generic CLI commands in new terminal windows. Parent skill category for agent and terminal spawning.
Teams using spawn 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/spawn/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How spawn Compares
| Feature / Agent | spawn | 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?
Skills for spawning external processes - AI coding agents and generic CLI commands in new terminal windows. Parent skill category for agent and terminal spawning.
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
# Spawn Skills
This directory contains skills for spawning external processes in new terminal windows.
## Overview
Spawn skills enable Claude Code to launch external processes:
- **AI coding agents** (Claude, Codex, Gemini, Cursor, OpenCode, Copilot)
- **Generic CLI commands** (ffmpeg, curl, python, npm, etc.)
Both use the `fork_terminal` utility to create isolated terminal sessions.
## Child Skills
| Skill | Description | Use Case |
|-------|-------------|----------|
| [agent](./agent/SKILL.md) | Spawn AI coding agents | Multi-provider orchestration |
| [terminal](./terminal/SKILL.md) | Spawn generic CLI commands | Non-AI command execution |
## When to Use
### Use spawn:agent when:
- Delegating tasks to external AI providers
- Need interactive CLI sessions with AI agents
- Browser-based authentication is required
- Real-time streaming output needed
### Use spawn:terminal when:
- Running non-AI CLI commands (ffmpeg, curl, etc.)
- Need interactive terminal for user input
- Long-running processes that shouldn't block Claude
### Use orchestration:native-invoke instead when:
- Automating multi-provider tasks
- Need parallel execution across providers
- Clean result collection is important
- No interactive/TTY requirements
## Core Utility
Both skills use the `fork_terminal` Python utility:
```python
# Located at: ./agent/fork_terminal.py
from fork_terminal import fork_terminal
# Basic usage
result = fork_terminal("command", capture=True)
# With logging
result = fork_terminal("command", log_to_file=True, log_agent_output=True)
```
## Quick Reference
```
spawn/
├── SKILL.md # This file
├── agent/ # AI agent spawning
│ ├── SKILL.md
│ ├── cookbook/ # Per-agent cookbooks
│ │ ├── claude-code.md
│ │ ├── codex-cli.md
│ │ ├── gemini-cli.md
│ │ ├── cursor-cli.md
│ │ ├── opencode-cli.md
│ │ └── copilot-cli.md
│ └── prompts/ # Reusable prompt templates
└── terminal/ # Generic CLI spawning
├── SKILL.md
└── cookbook/
└── cli-command.md
```
## Related Skills
- **orchestration/native-invoke** - Task-based CLI invocation (preferred for automation)
- **multi-agent-orchestration** - Higher-level provider routing
- **model-discovery** - Current model names for providers
## See Also
- `.claude/ai-dev-kit/dev-tools/orchestration/providers/` - Shell scripts for each provider
- `/ai-dev-kit:delegate` - Command for manual delegationRelated Skills
spawn-terminal
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.
spawn-agent
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
spawn-parallel
Pattern for spawning parallel subagents efficiently. Use when you need multiple independent tasks done concurrently.
Daily Logs
Record the user's daily activities, progress, decisions, and learnings in a structured, chronological format.
Socratic Method: The Dialectic Engine
This skill transforms Claude into a Socratic agent — a cognitive partner who guides
Sokratische Methode: Die Dialektik-Maschine
Dieser Skill verwandelt Claude in einen sokratischen Agenten — einen kognitiven Partner, der Nutzende durch systematisches Fragen zur Wissensentdeckung führt, anstatt direkt zu instruieren.
College Football Data (CFB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
College Basketball Data (CBB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
Betting Analysis
Before writing queries, consult `references/api-reference.md` for odds formats, command parameters, and key concepts.
Research Proposal Generator
Generate high-quality academic research proposals for PhD applications following Nature Reviews-style academic writing conventions.
Paper Slide Deck Generator
Transform academic papers and content into professional slide deck images with automatic figure extraction.
Medical Imaging AI Literature Review Skill
Write comprehensive literature reviews following a systematic 7-phase workflow.