🤖
AI EngineeringPython

Creating an Agent

by ed3dai

Creating an Agent is an AI Engineering skill for Claude Code, published by ed3dai in ed3d-plugins.

248 stars32 forkson ed3dai/ed3d-pluginsAdded 2026/09/02Repository updated 2026/06/16
claudeclaude-codeclaude-code-pluginclaude-code-plugin-marketplaceskills
Install in seconds
Install Creating an Agent
Copy Creating an Agent into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/creating-an-agent ~/.claude/skills/creating-an-agent

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/ed3dai/ed3d-plugins.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/ed3d-extending-claude/skills/creating-an-agent/SKILL.md in ed3dai/ed3d-plugins
Installs to
~/.claude/skills/creating-an-agent
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2631 skills

What Creating an Agent does

Creating an Agent explains how to design specialized subagents for Claude Code plugins or the Task tool. It covers trigger descriptions, tool limits, prompt structure, and testing agents.

Creating an Agent is cataloged under AI Engineering on DirSkills. Creating an Agent comes from a repository tagged claude, claude-code, claude-code-plugin, claude-code-plugin-marketplace and skills.

Documentation

README

Creating an Agent

REQUIRED BACKGROUND: Read ed3d-extending-claude:writing-claude-directives for foundational guidance on token efficiency, compliance techniques, and directive structure. This skill focuses on agent-specific patterns.

What is an Agent?

An agent is a specialized Claude instance with:

  • Defined tools (Read, Edit, Bash, etc.)
  • Specific responsibilities (code review, security audit, research)
  • A focused system prompt

Agents are spawned via the Task tool or defined in plugin agents/ directories.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Creating an Agent

  • What else does ed3dai publish alongside Creating an Agent?

    Creating an Agent is one of 25 skills that DirSkills catalogs from ed3dai/ed3d-plugins, the repository it ships in. Its siblings there include Asking Clarifying Questions, Brainstorming and Coding Effectively. Each one is a separate skill with its own page in this directory, installs the same way Creating an Agent does, and is maintained by ed3dai in that same repository. The rest of the collection is listed on the ed3dai/ed3d-plugins page.

  • How does Creating an Agent compare to other AI Engineering skills?

    Creating an Agent ranks #2315 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Creating an Agent against them. Open each page to compare what they document and how they install.

More from ed3dai/ed3d-plugins

Creating an Agent is one of 25 skills cataloged on DirSkills from ed3dai/ed3d-plugins.

See all 25 skills
1h ago

Asking Clarifying Questions

Asking Clarifying Questions helps narrow ambiguous requirements before brainstorming by resolving contradictions, defining scope, and checking assumptions. Use it after initial context is gathered to avoid designing the wrong solution.
AI Engineering
24832
💡
1h ago

Brainstorming

Brainstorming turns rough ideas into structured designs through guided questions, alternatives, and stepwise validation. Use it before implementation or planning to clarify goals, constraints, and approach.
AI Engineering
24832
🛠️
1h ago

Coding Effectively

Coding Effectively guides writing and refactoring code with correctness, explicit error handling, property-driven design, and clear module organization. Use it when implementing features, reviewing code, or choosing patterns across languages and runtimes.
Quality
24832
🧩
1h ago

Creating A Plugin

Creating A Plugin explains how to structure a Claude Code plugin and write its manifest. Use it when packaging commands, agents, skills, hooks, or MCP servers for reuse across projects.
AI Engineering
24832
🛡️
1h ago

Defense In Depth

Defense In Depth validates data at every layer it passes through so invalid values are caught by entry, business, environment, and debug checks. Use it when bad input causes failures deep in execution or tests bypass earlier validation.
Quality
24832
🧩
1h ago

Executing An Implementation Plan

Executing An Implementation Plan runs implementation plans phase by phase with fresh subagents for each task and review. It loads each phase just in time to reduce context use during multi-step work.
Automation
24832