skills.rest
RafalekS
RafalekSCOMMUNITY
Explore all skills by this author →
GitHub

agent-builder

Guide creation, refinement, and troubleshooting of Claude Code subagents.

1|Updated Feb 21, 2026
Search Tags:#troubleshooting#prompt engineering#ai development#agent#subagent#tool configuration
One-click install
npx skills add https://github.com/RafalekS/Claude_DB --skill agent-builder-rafaleks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-builder
Source: https://github.com/RafalekS/Claude_DB/tree/main/config/templates/skills/meta/agent-builder-skill
Command: npx skills add https://github.com/RafalekS/Claude_DB --skill agent-builder-rafaleks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides expert guidance for creating, improving, and troubleshooting Claude Code subagents, streamlining the development of specialized AI assistants.

Core Features & Use Cases

  • Agent Design: Offers best practices for defining agent scope, system prompts, and tool access.
  • Troubleshooting: Helps resolve issues with agent activation, tool permissions, and output formatting.
  • Use Case: You need to create a new subagent that can analyze code for security vulnerabilities. This Skill will guide you through defining its purpose, writing its system prompt, and configuring its tools.

Quick Start

Use the agent-builder skill to create a new subagent for analyzing code quality.

Frequently Asked Questions about agent-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Claude Code subagent for a specialized task?▼

You can create a subagent by defining its scope, writing a system prompt, and configuring tool access. This skill provides expert guidance on agent design and delegation patterns to help you build specialized AI assistants.

Why does my subagent fail to activate or use the right tools?▼

Subagent activation and tool permission failures usually stem from misconfigured system prompts or tool access settings. This skill helps troubleshoot these common problems by refining your agent configuration and output formatting.

What is the best way to write a system prompt for an AI agent?▼

The best way to write an AI agent system prompt is to clearly define its purpose and scope. This skill provides prompt engineering best practices to ensure your subagent understands delegated tasks and uses configured tools correctly.

Can I configure specific tool permissions for different subagents?▼

Yes, you can configure specific tool permissions for individual subagents. This skill provides tool configuration guidance, allowing you to restrict or grant tool access based on the specialized requirements of each AI assistant.

How do I fix output formatting issues with my custom AI assistant?▼

Fixing output formatting issues with your custom AI assistant requires refining its system prompt and delegation patterns. This skill helps troubleshoot and resolve formatting inconsistencies in your subagent responses.

Related Skills

Explore More Software Engineering Skills→
proyecto26proyecto26
42

requirements-scoping

Structure ambiguous system design prompts into functional requirements, non-functional constraints, and out-of-scope boundaries.

Official
Intermediate
full-stack-bizfull-stack-biz
26

subagent-creator

Create, validate, and refine Claude Code subagents with structured workflows.

Official
Advanced
tuanfungtuanfung

code-review-and-quality

Review code for correctness, readability, architecture, security, and performance.

Community
Advanced
velzicomvelzicom

agent-builder

Guide creation, refinement, and troubleshooting of AI subagents in Claude Code.

Official
Advanced