Create Subagents
Automatically generates specialized sub-agents to handle complex tasks, boosting efficiency and task completion rates.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add create-subagents npx -- -y @trustedskills/create-subagents
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"create-subagents": {
"command": "npx",
"args": [
"-y",
"@trustedskills/create-subagents"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
The create-subagents skill allows you to dynamically spawn specialized AI sub-agents from a parent agent. These child agents inherit context and tools while focusing on specific sub-tasks, enabling complex workflows without manual intervention.
When to use it
- Decomposing large, multi-step projects into manageable chunks for parallel processing.
- Assigning distinct roles (e.g., researcher vs. writer) to different parts of a conversation.
- Scaling operations by running multiple agents simultaneously on independent data sets.
- Isolating sensitive tasks within dedicated sub-agents to maintain context separation.
Key capabilities
- Instantly generates new agent instances from the current session.
- Inherited tools and knowledge are automatically available to child agents.
- Supports hierarchical task management where parents delegate specific instructions.
- Enables complex orchestration of multi-agent teams within a single workflow.
Example prompts
- "Create two sub-agents: one to analyze the sales data and another to draft the quarterly report."
- "Spawn a specialized coding agent to handle the backend logic while I continue discussing the frontend design."
- "Break down this research paper into three sub-tasks and create dedicated agents for literature review, methodology analysis, and conclusion drafting."
Tips & gotchas
Ensure your parent agent has sufficient context before spawning children, as they rely on inherited information. Monitor token usage carefully, as creating multiple simultaneous agents can increase consumption rates significantly.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.