Skip to content
TrustedSkillsbeta
Back to all skills

Create Subagents

Checked
glittercowboy·vlatest·agents·MIT

Automatically generates specialized sub-agents to handle complex tasks, boosting efficiency and task completion rates.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add glittercowboy/taches-cc-resources --skill create-subagents -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

glittercowboy

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned glittercowboy/taches-cc-resources at 1757615b99.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
1757615b99
Manifest
skills/create-subagents/SKILL.md
Scanned
8 files, 3,827 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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.