claudegoodies
Skill

agent-builder

From shareAI-lab

|

Provides design guidance and reference code (Python) for building agent loops with capabilities, knowledge, and context.

Use it when

  • Planning an agent's core loop and deciding which 3-5 capabilities to expose
  • Deciding whether to add planning, subagents, or skills to an agent
  • Scaffolding a new agent project with init_agent.py
  • Understanding agent architecture concepts like context isolation or progressive complexity

Skip it if

  • You need working production code, not a ~80-line reference example
  • You want a specific framework integration rather than general design principles
  • The content is conceptual guidance, not a ready-to-use tool or library

Facts

Repository
shareAI-lab/learn-claude-code
Status
Actively maintained
Last commit
Source file
skills/agent-builder/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# 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.

**Design principle**: Start with 3-5 capabilities. Add more only when the agent consistently fails because a capability is missing.

### 2. Knowledge (What does it KNOW?)

Domain expertise injected on-demand: policies, workflows, best practices, schemas.

**Design principle**: Make knowledge available, not mandatory. Load it when relevant, not upfront.

### 3. Context (What has happened?)

The conversation history - the thread connecting actions into coherent behavior.

**Design principle**: Context is precious. Isolate noisy subtasks. Truncate verbose outputs. Protect clarity.

## Agent Design Thinking

Before building, understa
View full source on GitHub →

Other skills