🤖
AI EngineeringPython

Agent Builder

by keyuchen21

Agent Builder is an AI Engineering skill for Claude Code, published by keyuchen21 in agentic-engineering-handbook.

184 stars16 forkson keyuchen21/agentic-engineering-handbookAdded 2026/09/06+1% in starsRepository updated 2026/08/03
agentic-engineeringagentsai-agentsanthropicclaude-codellmmcpopenai
Install in seconds
Install Agent Builder
Copy Agent Builder 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/keyuchen21/agentic-engineering-handbook/tree/main/tutorials/agent-loop/skills/agent-builder ~/.claude/skills/agent-builder

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/keyuchen21/agentic-engineering-handbook.git

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

In this catalog

Source file
tutorials/agent-loop/skills/agent-builder/SKILL.md in keyuchen21/agentic-engineering-handbook
Installs to
~/.claude/skills/agent-builder
Collection
One of 4 skills cataloged from this repository
Category
AI Engineering3278 skills

What Agent Builder does

Agent Builder helps you design and build AI agents for domains like research, operations, and creative work. Use it when you need agent architecture, tool use, subagents, planning, or Claude Code and Cursor internals.

Agent Builder is cataloged under AI Engineering on DirSkills. Agent Builder comes from a repository tagged agentic-engineering, agents, ai-agents, anthropic and claude-code.

Documentation

README

Agent Builder

Build AI agents for any domain - customer service, research, operations, creative work, or specialized business processes.

The Core Philosophy

The model already knows how to be an agent. Your job is to get out of the way.

An agent is not complex engineering. It's a simple loop that invites the model to act:

LOOP:
  Model sees: context + available capabilities
  Model decides: act or respond
  If act: execute capability, add result, continue
  If respond: return to user

That's it. The magic isn't in the code - it's in the model. Your code just provides the opportunity.

The Three Elements

1. Capabilities (What can it DO?)

Atomic actions the agent can perform: search, read, create, send, query, modify.

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

Frequently asked about Agent Builder

  • What else does keyuchen21 publish alongside Agent Builder?

    Agent Builder is one of 4 skills that DirSkills catalogs from keyuchen21/agentic-engineering-handbook, the repository it ships in. Its siblings there include Code Review, MCP Builder and PDF Processing. Each one is a separate skill with its own page in this directory, installs the same way Agent Builder does, and is maintained by keyuchen21 in that same repository. The rest of the collection is listed on the keyuchen21/agentic-engineering-handbook page.

  • How does Agent Builder compare to other AI Engineering skills?

    Agent Builder ranks #3029 by stars among the 3278 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 Agent Builder against them. Open each page to compare what they document and how they install.