agent-development

Design and build custom Claude Code agents with declarative prompts and tool delegation.

1|Updated Nov 26, 2025
One-click install
npx skills add https://github.com/slavochek2/claritypledge --skill agent-development-slavochek2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-development
Source: https://github.com/slavochek2/claritypledge/tree/main/.claude/commands/agent-development
Command: npx skills add https://github.com/slavochek2/claritypledge --skill agent-development-slavochek2

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designers and engineers often struggle to build Claude Code agents that can autonomously manage tasks, access tools safely, and document their behavior for future maintenance. This Skill provides a structured approach to creating self-documenting agent prompts, clear delegation rules, memory considerations, and scalable pipelines.

Core Features & Use Cases

  • Declarative agent prompts that control when and how agents are used.
  • Memory and state management guidance to prevent leakage and ensure reproducibility.
  • Patterns for building Task sub-agents, tool access policies, and agent pipelines in Claude Code.
  • Use Case: A developer designs an agent that handles code-review tasks with automatic delegation to specialized sub-agents.

Quick Start

Start by reading SKILL.md to understand the standard agent development patterns and craft your first declarative, self-documenting agent prompt.

Frequently Asked Questions about agent-development

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

FAQPage Schema
How do I design Claude Code agents for automatic task delegation?

Design Claude Code agents for automatic task delegation by writing declarative prompts that control when and how agents are used. This Skill provides structured patterns for creating self-documenting descriptions and safe tool access rules for auto-delegation.

What are the best patterns for managing memory and state in Claude Code agent pipelines?

Managing memory and state in Claude Code agent pipelines requires safe memory practices to prevent state leakage and ensure reproducibility. This Skill guides you in composing robust pipelines with declarative instruction design and clear memory considerations.

How do I configure tool access policies for Claude Code sub-agents?

Configure tool access policies for Claude Code sub-agents by applying scalable tool delegation patterns. This Skill helps you enforce safe tool delegation across projects by structuring self-documenting prompts that define explicit access boundaries.

Why does my Claude Code agent fail to trigger automatic delegation during code review?

Claude Code agent automatic delegation fails when agent descriptions lack effective declarative instructions. This Skill helps you diagnose and fix memory issues by crafting precise, self-documenting prompts that control agent triggering behavior.

Do I need specific dependencies to build scalable agent pipelines in Claude Code?

You do not need specific external dependencies to build scalable agent pipelines in Claude Code. This Skill operates independently, providing the structural guidance necessary to compose robust pipelines and enforce safe memory practices within your projects.